Sentiment Analysis in Social Streams

Hassan Saif, F. Javier Ortega, Miriam Fernández, Iván Cantador

Abstract In this chapter we review and discuss the state of the art on sentiment
analysis in social streams –such as web forums, micro-blogging systems, and so-
cial networks–, aiming to clarify how user opinions, affective states, and intended
emotional effects are extracted from user generated content, how they are modeled,
and how they could be finally exploited. We explain why sentiment analysis tasks
are more difficult for social streams than for other textual sources, and entail going
beyond classic text-based opinion mining techniques. We show, for example, that
social streams may use vocabularies and expressions that exist outside the main-
stream of standard, formal languages, and may reflect complex dynamics in the
opinions and sentiments expressed by individuals and communities.

1 Introduction

Sentiment Analysis is the field of study that analyzes the people’s attitudes towards
entities –individuals, organizations, products, services, events, and topics–, and their
attributes [36]; The attitudes may correspond to personal opinions and evaluations,
affective states (sentiments and moods), or intended emotional effects. It represents
a large problem space, covering different tasks, such as subjectivity identification,
sentiment extraction and analysis, and opinion mining, to name a few.

Hassan Saif
Knowledge Media Institute, Milton Keynes, United Kingdom, e-mail: [Link]@[Link]
F. Javier Ortega
Universidad de Sevilla, Seville, Spain, e-mail: javierortega@[Link]
Miriam Fernández
Knowledge Media Institute, Milton Keynes, United Kingdom, e-mail: [Link]@[Link]
Iván Cantador
Universidad Autónoma de Madrid, Madrid, Spain, e-mail: [Link]@[Link]

1
2 Hassan Saif, F. Javier Ortega, Miriam Fernández, Iván Cantador

Although some of the above tasks have been addressed on multi-modal data
sources –e.g., sentiment extraction in audio and video–, from its origins, sentiment
analysis has mainly focused on textual data sources [48]. Hence, it commonly refers
to the use of natural language processing, text analysis, and computational linguis-
tics to extract and exploit subjective information from text materials. In Chapters ??
and ?? the reader can find overviews of the state of the art in affective information
representation and acquisition for various modalities.
With the advent of the Social Web , the amount of text material is huge and grows
exponentially every day. The Web is a source of up-to-date, never-ending streams
of user generated content; people communicate online with contacts in social net-
works, create or upload multimedia objects in online sharing sites, post comments,
reviews and ratings in blogs and recommender systems, contribute to wiki-style
repositories, and annotate resources in social tagging platforms.
The Web thus provides unstructured information about user opinions, moods and
emotions, and tastes and interests, which may be of great utility to others, includ-
ing consumers, companies, and governments. Hence, for instance, someone who
wants to buy a camera may look in web forums for online opinions and reviews
about different brands and models, while camera manufacturers implicitly/explicitly
get feedback from customers to improve their products, and adapt their marketing
strategies. qVery interestingly, this information can go beyond reflecting the users’
subjective evaluations and sentiments about entities and their changes over time, by
triggering chains of reactions and new events. For instance, identifying the over-
all concern, expressed in social media, on certain political decision may impact the
modification or rejection of such decision.
The interest and potential exploitation of sentiment analysis in social streams –
understood as social media in which user generated content emerges and changes
rapidly and constantly–, are evident, and have been shown in numerous domains and
applications, like politics and e-government [6][45][77], education and e-learning
[76], business and e-commerce [85], and entertainment [23][72][80]. The reader is
referred to several chapters of this book for detailed surveys of particular applica-
tions of affective information by personalized services, specifically by recommender
systems (Chapters ??, ?? and ??), conversational systems (Chapter ??), multimedia
retrieval systems (Chapters ?? and ??), and e-learning systems (Chapter ??).
The high availability of user generated content in social streams, nonetheless,
comes with some challenges. The large volume of data makes difficult to get the rel-
evant information in an efficient and effective way. Proposed techniques have to be
simple enough to scale up, but have to deal with complex data. Some of these chal-
lenges are related to general natural language processing (NLP) approaches, such as
opinion-feature association [31], opinion negation [32], irony and sarcasm [12][18],
and opinion spam [33]. Others, in contrast, are related to issues characteristic of
online user generated content, such as multiple languages, high level of ambiguity
and polysemy, misspellings, and slang and swear words [70]. In this context, it is
also important to mention the need of determining the users’ reputation and trust.
For certain topics, the majority opinion (i.e., the wisdom of the crowd) may be the
best solution [49], while for others, only the experts’ opinions should be the source
Sentiment Analysis in Social Streams 3

of information to consider [87]. Another relevant issue is the existence of particu-

lar pieces and forms of information existing in social streams: explicit citations to
users, groups and organizations (e.g., @robinwilliams in Twitter), explicit forms for
referring to concepts (e.g., Twitter hashtags #comedian and #funny), emoticons and
slang terms noting emotions and moods (e.g., :D and lol), mechanisms to express
interests and tastes (e.g., Facebook likes), and URLs to resources that complement
posted information. There, the use of contextual metadata also plays a key role;
extracting and mining time and geo-location metadata may be very valuable for
sentiment analysis on dynamic and global social stream data.
In this chapter, we review and discuss the state of the art on sentiment analysis in
social streams, describing how opinion and affective information is extracted, pro-
cessed, modeled, and exploited, in comparison to classic text-based opinion mining
techniques.
The chapter is structured as follows. In Section 2 we overview the research lit-
erature in Sentiment Analysis, focusing on the main addressed tasks and applied
techniques. In Section 3 we provide a description of social media, characterizing
the user generated content and research challenges that arise from them. Next, in
Section 4 we discuss Sentiment Analysis to social streams, and describe existing
applications in such context. Finally, in Section 5 we discuss current and open re-
search trends on Sentiment Analysis in social streams.

2 Sentiment Analysis

In the last fifteen years, Sentiment Analysis and Opinion Mining have been fed by a
number of research problems and opportunities of increasing importance and inter-
est [48]. In this section we review the main tasks addressed in the literature related to
sentiment analysis, together with the different assumptions and approaches adopted.
We then discuss some interesting proposals, resources and techniques intended to
deal with those tasks.

2.1 Sentiment Analysis Tasks

The different sentiment analysis tasks can be categorized based on the granularity of
their linguistic units they consider. In this sense, there are tasks where the document
is assumed to be the main linguistic unit as a whole, while there are others where
sentences or even words are considered as linguistic units. We can summarize these
levels as follows:
• Document-level: At this level, it is assumed that each document expresses a par-
ticular sentiment, or at least it poses a predominant one. Many works have faced
sentiment analysis tasks at the document level; see for example the survey pre-
sented in [78].
4 Hassan Saif, F. Javier Ortega, Miriam Fernández, Iván Cantador

• Sentence-level: Some tasks could benefit from the determination of the senti-
ment in a text at a sentence level, as done in information extraction and question
answering systems, where it is necessary to provide the user with particular in-
formation for a given topic.
• Aspect-level: In general, a sentence can contain more than one opinion about dif-
ferent aspects of an entity or topic. In an aspect-level approach, the context of
the words are taken into account to determine the subjectivity of each expression
in a sentence, and the specific aspect being opinionated [82][84]. This level can
be useful, for example, in recommender systems [13], and in automatic process-
ing of product reviews [16][44], where knowing individual opinions about each
feature of a given product is crucial for the performance of the system.
• Word-level (also called as entity level): In this category we can find those tasks
consisting of identifying the sentiment expressed by a given word regardless it
context. Word-level analysis is useful in order to build resources like sentiment
lexicons with the possible sentiment orientations of a word [29][64].
Another possible classification of sentiment analysis tasks can be made from
the point of view of the dependency on the target domain. While some tasks are
defined independently of the domain of application –like subjectivity detection–,
some research works have shown the influence of domain-dependency on sentiment
analysis problems –e.g., polarity detection [16][53][52][83].
In general, the following are the main goals of sentiment analysis:
• Subjectivity detection. Identifying subjective and objective statements.
• Polarity opinion detection. Identifying positive and negative opinions within sub-
jective texts.
• Emotion detection. Identifying human emotions and moods.
Subjectivity detection can provide valuable knowledge to diverse NLP-based ap-
plications. In principle, any system intended to extract pieces of information from
a large collection of texts could take advantage of subjectivity detection approaches
as a tool for identifying and considering/discarding non-factual information [57].
Such is the case of question answering [86] and information extraction systems.
Polarity detection aims to identify whether a text expresses a positive or a neg-
ative sentiment from the writer. Since it is very common to address this task only
on subjective texts, usually a subjectivity detection stage is needed. Hence, in the
literature we can find a number of works that tackle both problems –subjectivity
and polarity detection– as a single one. Existing approaches commonly distinguish
between three types of texts: positive, negative, and neutral or objective texts. Some
works have shown this approach is much more challenging than the binary classi-
fication of subjective texts [57]. Applications of polarity classification are the iden-
tification of the writer’s political ideology –since it can be considered as a binary
classification problem [21]–, and the analysis of product reviews –determining user
positive or negative opinions about a given item (a product, a movie, a hotel, etc.)
or even personal sentiments about specific features of such item.
In emotion detection, the main object of study is the user’s emotional attitude
with respect to a text. In this context, we may aim to determine the writer’s mood
Sentiment Analysis in Social Streams 5

towards a text [82] or to identify the emotions “provoked” by the text to the reader
[68].

2.2 Sentiment Analysis Approaches

In this section we discuss some interesting approaches intended to deal with the
sentiment analysis tasks and goals previously described. For the sake of clarity, we
classify them into two groups, according to the nature of the applied techniques:

• Lexicon-based approaches are those techniques that rely on a resource contain-

ing information about the affective terms that may occur in the texts, and usu-
ally additional information about such terms (e.g., polarity, intensity, etc.). These
resources can be manually or automatically generated, domain independent or
focused on a particular domain. Most of these approaches take advantage of the
information available in a lexicon to compute subjective and affective estimations
over the texts.
• Machine Learning approaches are those techniques that apply a machine learn-
ing method to address sentiment analysis tasks. In this case, a majority of tech-
niques have been based on Support Vector Machines, which are usually fed with
lexical and syntactic features, or even with lexicon-based features, to provide
subjective and affective classifications.
It is worth to note that the creation, integration and use of lexicons are crucial
in Sentiment Analysis, not only for lexicon-based techniques, but also for machine-
learning techniques, which can be enhanced with the information available in such
resources. In this context, General Inquirer [69] can be considered as one of the
most relevant and widely used resources. It is a manually built lexicon formed by
lemmas with associated syntactic, semantic and pragmatic information. It contains
4, 206 lemmas manually tagged as positive or negative.
The MPQA (Multi-Perspective Question Answering) is a lexicon of news doc-
uments from the world press based on General Inquirer, including a set of words
obtained from a dictionary and a thesaurus, and a set of automatically compiled
subjective terms [57]. The MPQA lexicon is composed by 8, 222 words with a set
of syntactic and semantic features (type strength, length, part of speech, stem, and
prior polarity).
Following the same schema, the Bing Liu’s English Lexicon (BLEL) [30] con-
sists of an automatically generated list of words that have been classified into pos-
itive and negative. This classification is manually updated periodically. In total,
BLEL contains 4, 783 negative words and 2, 006 positive words, including mis-
spelled terms, morphological variants, and slang words, among others.
Maybe one of the most well-known and widely used lexical resources is Word-
Net [42], a thesaurus for English based on the definition of the so-called synsets,
which are groups of words with the same meaning and a brief definition (gloss). To
6 Hassan Saif, F. Javier Ortega, Miriam Fernández, Iván Cantador

relate synsets, WordNet provides a number of semantic relations, such as synonymy,

hypernonymy, and meronymy.
A very large number of works have used WordNet in a wide number of tasks and
domains, and some of them have aimed to enrich or expand WordNet in different
ways. In this context, it is worth to mention the Global WordNet Association1 , a
non-commercial organization devoted to provide a platform to ease the creation and
connection of WordNet versions in different languages. Regarding the enrichment
of WordNet, we can highlight WordNet Domains [5], a semi-supervised generated
resource that augments WordNet with domain labels for all its synsets. Related to
it, we find WordNet Affect [67], which assigns to each WordNet synset a set of af-
fective labels encoding emotions, moods, attitudes, behaviors, etc. in order to build
a resource suitable for emotion detection, in addition to subjectivity and polarity
classification. Another affective extension of WordNet is SentiWordNet (SWN) [4],
which attaches to each WordNet synset three sentiment scores in the range [0, 1]
summing up to 1, representing positivity, negativity and objectivity degrees of each
synset. The polarities of words are assigned by means of a propagation of the po-
larity of some manually picked synsets through the relations in WordNet. SWN
includes 117, 000 synsets with sentiment scores.
The main advantage of WordNet-based resources and techniques over MPQA,
BLEL or General Inquirer is the lack of semantic ambiguity between synsets, which
unequivocally represent the term meaning. Word sense disambiguation constitutes
a crucial problem in NLP, and most of the works using the above lexicons address
such problem by computing the polarity at the level of words or lemmas by means
of the polarity values from all the respective synsets [1][71]. In addition to this,
the graph structure of WordNet-based resources allows for the application of graph-
based techniques in order to better exploit the semantic information encoded within
the relations.
Among the existing lexicon-based approaches, the technique presented in [78]
has been a main reference work for many others. This technique is applied over
manually selected sets of strongly positive words (such us excellent and good) and
strongly negative words (such as poor and bad), which are considered as seed terms.
The technique computes the Pointwise Mutual Information (PMI) between input
words and the seeds in order to determine the polarity of the former. Since the po-
larity of a word depends on the relation between the word and the seed sets, the
technique is usually called semantic orientation by association. A similar idea is
proposed in [34], but replacing the PMI computation by building a graph with the
adjectives in WordNet for computing the polarity of a word; specifically, by select-
ing the shortest graph path from the synset of the word to the synsets of the positive
and negative seeds.
With respect to machine learning-based approaches, a considerable number of
works has been done, applying well-known machine learning techniques, such as
SVM and LSA, to deal with sentiment analysis tasks. These works usually include
the exploitation of lexical, syntactic and semantic features suitable for the classifica-

1 [Link]
Sentiment Analysis in Social Streams 7

tion problems that must be tackled in sentiment analysis for the subjectivity and po-
larity detection. Among these features, one may highlight n-grams, Part-Of-Speech
(POS) tags, PMI and features extracted from lexicons [19][84]. In this context, it has
to be noted that the joint use of lexicon- an machine learning-based approaches can
be performed in the opposite direction, i.e., by using machine-learning techniques in
order to improve lexicon-based approaches. For instance, in [51] LSA-based tech-
niques are used to expand a given lexicon for different languages.
The work presented in [29] is another representative example of a machine
learning-based sentiment analysis approach. It aims to predict the orientation of
subjective adjectives by analyzing a large unlabeled document set, and looking for
pairs of adjectives linked with conjunctions. It then builds a graph where the nodes
correspond to terms connected by equal-orientation or opposite-orientation edges,
according to the conjunctions that link the terms, and finally apply a clustering al-
gorithm that partitions the graph into clusters of positive and negative terms.
A combination of ideas from Turney [78] and Hatzivassiloglou [29] is presented
in [15], where a set of seed words is used to introduce a bias in a random-walk
algorithm that computes a ranking of the terms in a graph of words linked according
to the conjunctions that join them in the texts. In the generated rankings, positive
and negative terms are respectively located into the highest and lowest positions.
The word graph is also used as a mechanism to process the negations in the text
by developing a PageRank-based algorithm that builds graphs with positive and
negative weighted edges.

3 Sentiment Analysis on User Generated Content

Online social media platforms support social interactions by allowing users to create
and maintain connections, share information, collaborate, discuss, and interact in a
variety of ways. The proliferation and usage of these platforms have experienced an
explosive growth in the last decade, expanding to all areas of society, such as enter-
tainment, culture, science, business, politics, and public services. As a result, a large
amount of user generated content is continuously being created, offering individuals
and organizations a fast way to monitor people’s opinions and sentiments towards
any form of entity, such as products, services and brands.
The nature and purpose of these platforms is manifold, and thus they differ in a
variety of aspects, such as the way in which users establish connections, the main
activities they conduct, and the type of content they share. These characteristics
pose novel challenges and opportunities to sentiment analysis researchers. In the
subsequent sections, we characterize the user generated content available in popular
types of existing social media platforms, and present the major challenges to process
such content in the context of sentiment analysis and opinion mining.
8 Hassan Saif, F. Javier Ortega, Miriam Fernández, Iván Cantador

3.1 Characterizing User Generated Content

In the literature, social media platforms have been categorized in different ways
[35]2 . Here we propose a categorization based on three dimensions: the type of user
connections, the type of user activities, and the type of contents generated/shared
within the platforms. We summarize such a categorization in Table 1.
• Connections: Users connections –e.g., friendship and following relations– in so-
cial media are based on three main models: explicit connections, which can be
reciprocal –u follows v, and v follows u– and non-reciprocal –u follows v, but
not necessary v follows u–, and implicit connections, where relations are ex-
tracted via interactions in the social platform –e.g., if user u posts a message and
user v replies to that message, an implicit relation between v and u may be as-
sumed. An example of a social platform that uses explicit reciprocal connections
is Facebook3 via its friendship relations. Twitter4 , differently, uses explicit non-
reciprocal connections via its follower-followee relation; if a user u follows a
user v on Twitter, it does not necessarily imply that v follows u. Implicit connec-
tions, on the other hand, are more common in forums and blogs, where users post
questions, evaluations or opinions, and other users react to the posted content.
• Activities: Users may perform different activities and have different goals when
participating in a social media platform. In this chapter we mainly focus on five
activities: nurturing social connections, discussing about particular issues and
topics, asking for information, sharing content and, collaborating with others for
certain tasks. Note that the majority of social media may allow performing vari-
ous of these activities.
• Types of contents: The third dimension to categorize social platforms is the type
of content that users share between them. Here we distinguish between six main
types: text, micro-text, tags, URLs, videos and images. Text and micro-text con-
tents differ on their number of characters. Micro-text is characteristic of micro-
blogging platforms, such as Twitter, which allows a maximum of 140 characters
in their text messages. Note that, as with activities, many of the existing platforms
allow for multiple combinations of these content types, although their focus tends
to be on few of them.
According to these three dimensions, social platforms can be described as fol-
lows:
• Forums: Forums and discussion boards are mainly focused on allowing users to
hold conversations and to discuss about particular issues and topics. A user gen-
erally posts an comment, opinion or question, and other users reply, starting a
conversation. All the posts related to a conversation are grouped into a structure

2 [Link]
[Link]
3 [Link]
4 [Link]
Sentiment Analysis in Social Streams 9

Table 1 Main characteristics of particular social media.

Social media
Social
Forums Q&A Wikis Blogs Micro- Social tagging
systems blogs networks
systems
Reciprocal x x x
User Explicit
Non-reciprocal x
connections
Implicit x x x x
Nurturing x
social connections
Discussing x x x x
Actions issues and topics
Asking x x
for information
Sharing x x x x x x
content
Collaborating x
in tasks
Text x x x x x
Micro-text x
Contents Tags x x
URLs x x x x x x
Videos x x x x
Images x x x x

called thread. The predominant type of content in these platforms is the text gen-
erated with the evolution of the users’ discussions. User connections in forums
usually are implicit. In general, users are not “friends” with each other explicitly,
but connections between them can be extracted from the question-reply chains
of their discussions. An example of this type of social platform is Boards.ie5 , a
popular Irish public forum board system, which is not restricted to certain topic,
and where users discuss about any domain or topic, e.g., politics, sports, movies,
TV programs, and music.
• Q&A systems: Question Answering (QA) platforms can be understood as a par-
ticular type of forums, where the main goal of their users is to ask for information,
and therefore discussions are generated around the answers to formulated ques-
tions. A popular example of QA system is Stack Overflow6 , where users ask a
variety of questions about computer programming. A particular characteristic of
Stack Overflow and other QA platforms, is that users can gain reputation points
based on the quality of their contributions.
• Wikis: The key goal of wikis is to enable collaboration between users in order
to create content (ideas, documents, reports, etc.). Users are therefore allowed to
add, modify and delete content in collaboration with others. Connections in this
type of platforms are generally implicit, and are derived from common editing of

5 [Link]
6 [Link]
10 Hassan Saif, F. Javier Ortega, Miriam Fernández, Iván Cantador

a particular resource: a wiki page. The main type of content generated in wikis is
text, but other content types, such as images and URLs, are also quite common.
One of the most popular examples of this type of platforms is Wikipedia7 , a wiki
with more than 73,000 editors around the world, who have contributed to the
creation of a very large open online encyclopedia.
• Blogs: Blogs represent a more “personal” type of platform with respect to forums
and wikis. When using these platforms, the main goal is to share information, al-
though this often generates discussions. A user does not participate in a blog, but
owns it, and uses it to share explanations, opinions or reviews about a variety of
issues. Other users can comment about particular blog posts, sometimes gener-
ating large discussions. Differently to forums, these discussions are not grouped
into threads, but are located under a particular blog post. Multimedia content
(photos, videos) are also frequent within this type of platforms. Popular exam-
ples of blogging platforms are Blogger8 and WordPress9 .
• Microblogs: Microblogs can be considered as a particular type of blog, where the
posted content typically is much smaller. Microblogs are also focused on sharing
information, but in this case, information is exchanged in small elements, such as
short sentences, individual images, videos, and URLs. As opposed to blogs, mi-
croblogs generally allow for explicit user connections, both reciprocal and non-
reciprocal. One of the most popular micro-blogging platforms is Twitter, which
allows a maximum message length of 140 characters. This limitation forces users
to use abbreviations and ill-formed words, which represent important challenges
when analyzing sentiments and opinions.
• Social networks: The main goal of social networks is to maintain and nurture
social connections. With this purpose they enable the creation of explicit, recip-
rocal relations between users. Most of these platforms also support other types of
activities, such as sharing content and enabling discussions. In this sense, users
share text, URLs and multimedia content within a platform. Popular examples of
social networks are LinkedIn10 , which is focused on professional connections,
and Facebook, which tends to be more focused on personal relations.
• Social tagging systems: In these platforms, users create or upload content (e.g.,
images, audios, videos), annotate it with freely chosen words (called tags), and
share it with others. The whole set of tags constitutes an unstructured collab-
orative categorization scheme, which is commonly known as folksonomy. This
implicit categorization is then used to search for and discover resources of inter-
est. In principle, social tagging systems are not conceived for connecting users.
Nonetheless, the shared tags and annotated items are usually used to find implicit
relations between users based on common interests and tastes. Moreover, tags do
not always describe the annotated items, but reflect personal opinions and emo-

7 [Link]
8 [Link]
9 [Link]
10 [Link]
Sentiment Analysis in Social Streams 11

tions concerning such items [10]. Popular sites with social tagging services are
Flickr11 , YouTube12 and Delicious13 .
Note that our purpose is not to provide an exhaustive categorization of social me-
dia, but an overview of the main types of platforms used in the literature to extract
and capture opinion and affective information. Other categorizations and platforms
exist, such as social bookmarking systems and multimedia sharing sites. In the fol-
lowing subsection, we explain the challenges and opportunities that social media
content poses to the extraction and analysis of the above information.

3.2 Challenges of Sentiment Analysis in Social Media

Content generated by users via social media in general, and micro-blogging plat-
forms in particular, poses multiple challenges to sentiment analysis [38][60]. In this
section we aim to overview and summarize some of these challenges.
• Colloquial language: Social platforms, except those targeting professional cir-
cles, are commonly used for informal communication. Colloquial written lan-
guage generally contains spelling, syntactical and grammatical mistakes [73]. In
addition, users tend to express their emotions and opinions using slang terms,
emoticons, exclamation marks, irony and sarcasm [38]. Processing ill-formed
text, understanding the semantics of slang language, emphasizing the detected
emotion/opinion level according to exclamation marks, and detecting that the
emotion expressed by a user is the opposite than the emotion reflected within the
text due to sarcasm, represent difficult challenges for current NLP and sentiment
analysis tools.
• Short texts: Small pieces of text are typical in micro-blogging platforms, such as
Twitter, where a maximum of 140 characters per message is allowed. To con-
dense their messages, users make use of abbreviations (e.g., lol for laugh out
loud), ill-formed words (e.g., 2morrow for tomorrow), and sentences lacking syn-
tactical structure (e.g., TB Pilot Measuring up (Time):<1 week from data shar-
ing). The lack of syntactical structure, as well as the appearance of abbreviations
and contemporaneous terms not recorded in dictionaries, represent important
challenges when attempting to understand the affective information expressed
within the texts [60].
• Platform-specific elements: Some social platforms have their own symbols and
textual conventions to express opinions (e.g., Facebook “likes”, Google+ “+1”,
and StackOverflow points to reward high quality answers), topics (e.g., Twitter
hashtags), and references to other users (e.g., Twitter @ symbol). To exploit these
conventions, sentiment analysis methods and tools have to be adapted [75].

11 [Link]
12 [Link]
13 [Link]
12 Hassan Saif, F. Javier Ortega, Miriam Fernández, Iván Cantador

• Real-time Big Data: User generated content coming from popular social media,
such as Facebook and Twitter, is characterized by the Big Data challenges, in-
cluding: volume –data size–, velocity –the speed of change–, variety –different
types of data–, and veracity –the trustworthiness of the data. Hence, sentiment
analysis techniques applied to social media platforms have to deal with: process-
ing massive amounts of data in short periods of time, dealing with the constant
emergence of new words and topics, managing data in different formats (text,
image, video), and assessing the veracity of data sources [7][8][65]. From these
aspects, we highlight the velocity aspect, which implies not only to capture and
process the user generated content in real time, but also to perform a response
(e.g., recommendation, news provision, trending topic detection) as fast as pos-
sible, since it is a common demanding functionality from social media users.

4 Sentiment Analysis in Social Streams

Once presented the main Sentiment Analysis tasks and techniques (Section 2), and
described the characteristics of user generated content with regards to the expression
of personal opinions and sentiments (Section 3), in the subsequent sections we focus
on particular problems and applications of Sentiment Analysis in social streams.

4.1 Sentiment Analysis Problems Addressed in Social Streams

Sentiment Analysis is an essential processing task for personalized services that aim
to exploit textual content –such as microblog messages and social tags– generated
in social streams, since they usually reflect the users’ subjectivity, in terms of opin-
ions and sentiments for certain issues and topics. For such purpose, in addition to
the fundamental sentiment analysis problems –such as entity and opinion recogni-
tion, and sentiment polarity estimation–, there are aspects that have to be taken into
account. User-generated content in social streams presents a number of interesting
phenomena, namely opinion spam, user reputation, irony, sarcasm, and emotion dy-
namics. If we intend to address these issues, we have to go beyond classic text-based
opinion mining techniques.
Opinion spam [33] is aimed to disturb the normal behavior in social media ser-
vices, especially those integrated in recommendation and e-commerce systems, by
introducing a bias towards a specific opinion tendency that promotes or demotes an
entity (e.g., a product, a service, a brand), or makes users express reviews and opin-
ions in a certain direction. The identification of opinion spam represents a crucial
problem for opinion mining and sentiment analysis approaches, which should be
able to detect deceptive opinions that try to simulate real user reviews that increase
or harm an entity’s reputation [28][47]. In certain media, such as social networks
and microblogging platforms, the users’ responses (e.g. by unfollowing contacts,
Sentiment Analysis in Social Streams 13

and posting complaint comments) may represent a valuable source of information

to detect spam content.
The writers’ reputation is another important aspect of sentiment analysis of user-
generated content. From the point of view of a review site, the higher the reputation
of a review author, the more reliable the review can be to other customers, and
sometimes vice versa: A review that is seen as reliable by the users can provide
high reputation to its author. In this sense, determining the reputation of the au-
thors of a content can be helpful for opinion spam detection. Moreover, some sites
have adopted reputation systems as a tool for avoiding or at least discouraging the
production of opinion spam. The reputation of users also plays an important role
in social networks, since automatically determining the most influential users in a
given network can be really valuable [20].
Given the subjective nature of user-generated content, another relevant phe-
nomenon is the existence of irony or sarcasm in the texts. This can constitute a
serious problem for many tasks in Sentiment Analysis, like detection of subjectivity
and the classification of the polarity of a given opinion, since the explicit text con-
tent reflects the opposite of the sentiment really expressed by the writers. Most of
published works has focused on the identification of one-liners (jokes or humorous
contents in short texts), but there are some researches aimed to extract humorous
patterns from longer texts. In a different way, there are also approaches that use
results of sentiment analysis in order to detect humor in texts, for example the (neg-
ative) polarity of a text has been taken as a feature to retrieve patterns of humorous
contents [41], and syntactic and semantic features have been used as indicatives
of humor [56], e.g., semantic ambiguity, the appearance of emoticons, idioms and
slang language, and the abundance/absence of punctuation marks, to name a few. In
the case of social media, certain user responses, such as expressions of amusement
and laughing emoticons, may be used as a source for identifying contents with irony
and sarcasm, which may be difficult to detect if no additional information apart from
the contents themselves exist.

4.2 Applications of Sentiment Analysis on Social Streams

Sentiment analysis over social platforms offers a fast and effective way to monitor
the public’s opinions and feelings towards products, brands, governments, events,
etc. Such insights can be used to support decision making in a variety of scenar-
ios. In this section we present three scenarios where the extraction and exploitation
of affective information from social streams have become key for certain decision
making tasks.
• Sentiment Analysis in politics and e-government: Designing and implementing
a policy at any level of government is a complex process. One of the key dif-
ficulties is finding and summarizing public opinions and sentiments. Citizens
do not actively participate in e-government portals [43], and policy specialists
14 Hassan Saif, F. Javier Ortega, Miriam Fernández, Iván Cantador

lack of appropriate tools to take into account the citizens’ views on policy is-
sues expressed in real time through social network discussions. Governments are
currently investing in research and development14 to learn about the citizens, by
summarizing public opinion via popular social platforms, and to engage them
more effectively. One of the key challenges that arises from this scenario is the
lack of awareness of the characteristics of those users that discuss politic issues
in social media, and whether those users really represent the public opinion [24].
Sentiment analysis tools are therefore challenged in this scenario to complement
affective information with details about the citizens and organizations behind the
gathered opinions. Another common task in which social streams are used as a
source of affective and opinion information about politics is the prediction of
the outcome and evolution of events, such as elections [45][77], and crises and
revolutions [6], as in the case of the Westgate Mall Terror Attack in Kenya [66].
• Sentiment Analysis in education and e-learning: Schools and universities strive
to collect feedback from students to improve their courses and tutorship pro-
grams. Such feedback is often collected at the end of a course via survey forms.
However, such methods are too controlled, slow, and passive. With the rise of
social streams, many students are finding online social streams as perfect venues
in which sharing their experiences, and seeking for peer help and support. To
address this issue, educational institutions –such as the Open University15 – are
working towards the development of platforms that allow capturing and moni-
toring the students’ sentiment and opinion in open social media groups [76]. The
aim is to speed up the reaction to the concerns and challenges raised by students.
In this scenario, one of the key challenges that arises is the need for adapting the
sentiment and opinion extraction processes to the particularities of the domain.
For example, discussions around a World War lecture will generally have a neg-
ative connotation. Sentiment analysis tools need to isolate the opinions targeting
the logistics of a course, with respect to the opinions targeting themes inherent
to the course.
• Sentiment Analysis in business and e-commerce: Public as well as corporate so-
cial platforms generate major economic value to business, and can form pivotal
parts of corporate expertise management, corporate marketing, product support,
customer relationship management, product innovation, and targeted advertising.
Public social platforms are generally used to monitor public opinion and reputa-
tion about brands and products [85]16 . Corporate social platforms, on the other
hand, are more focused on providing product support and knowledge interchange
within a company. One of the new challenges associated with managing these
on-line communities is the ability to predict change in their “health”. Providing
owners and managers of the social platforms with early warnings (by monitoring
the members’ contributions, opinions, levels of satisfaction, etc.) may facilitate
their decisions to safeguard the communities, e.g. by maintaining engagement,

14 [Link] [Link]
15 [Link]
16 [Link] [Link]
Sentiment Analysis in Social Streams 15

reducing community churn, and providing adequate support. The identification

of sentiments is key as an initial indicator, but it does not necessarily represent
the overall health of the community. The challenge of sentiment analysis tools
in this scenario is to complement sentiment extraction with techniques for risk
detection in the context of business domains, helping owners and hosts to ensure
a sustained stability of their communities.
• Sentiment Analysis in entertainment: In an online entertainment scenario, it is
well accepted that (i) the user’s current mood may affect the type of resource
(e.g., a song, a tv series episode, a video game) she prefers to consume at a par-
ticular time –partial or completely regardless her personal tastes– and, in the op-
posite direction, that (ii) emotions evoked by consumed resources may affect the
user’s current mood. These facts are the basis for the investigation and develop-
ment of sentiment-aware engaging services in social media. How user moods and
item-provoked emotions can be determined [25], how they can be related each
other [88], and how they and their relations can be exploited for user entertain-
ment applications are indeed emerging research topics, such as those addressed in
recommender systems [72], and multimedia retrieval and entertainment [23][80].
All these application scenarios come with an additional common challenge: scal-
ability. Social platforms can easily exceed a million users with hundreds of thou-
sands online each day. Content generation may be of Gigabytes per day, and orders
of magnitude more data is derived from observing interaction of the users within
a system. Existing data analysis approaches, and in particular sentiment analysis
tools, currently struggle with these scalability challenges.

5 Discussion

In the previous sections, we have reviewed and discussed the state of the art on
sentiment analysis in social streams. We have explained the different types of user
generated content existing in social media platforms, as well as some of the most
common challenges that this type of content poses when analyzing affective and
opinion information. We have described the different problems and tasks addressed
in the sentiment analysis research area, as well as the variety of techniques that
have been developed to approach them. We have shown examples of applications
that use sentiment analysis on social streams to support decision making process
in a variety of domains. In this section, we provide an overview of directions that
sentiment analysis area is currently following, and what are the main factors driving
the research into these directions.
• Sentiments are dynamic: Social streams, such as Twitter, may exhibit very strong
temporal dynamics with opinions about the same entity or event changing rapidly
over time. Since sentiment analysis approaches generally work by aggregating in-
formation, a key challenge faced by current sentiment analysis approaches is to
detect when new opinions are emerging, so that the new information is not aggre-
16 Hassan Saif, F. Javier Ortega, Miriam Fernández, Iván Cantador

gated to an existing opinion for the given entity. For example, the opinion about
the Nexus4 smartphone is generally determined based on a set of posts express-
ing sentiment about this particular device. Opinions about it may change over
time, e.g., as new technical problems or bugs are discovered. Sentiment analy-
sis approaches should therefore be able to identify opinion changes for entities
and/or events as long as new issues regarding them emerge. An option adopted by
several approaches is to define a time-window (minute, hour, day) in which sen-
timent is aggregated for the particular entity that is being monitored. However,
discussions in social media may emerge and spread really fast, or cool down for
long time periods. Therefore, assessing the right granularity level is key to not
loose relevant information when discussions spike, and not waste resources when
discussions about target entities or events are not present [7][39].
• Sentiments are entity-focused: As discussed in Section 2, sentiment is generally
computed at document and/or sentence level. Multiple sentiments, nonetheless,
can be expressed within the same document or the same sentence towards dif-
ferent targets. For example, the post “I love Nexus4 but I don’t like Nexus5 at
all!” expresses two different sentiments towards two different targets, the Nexus4
and Nexus5 devices. Additionally, when monitoring the sentiment or particu-
lar brands, events or individuals in social media, sentiment analysis approaches
should consider if the sentiment of the posts referencing the brand, event or indi-
vidual do indeed express sentiment towards those entities. For instance, a signif-
icant number of negative posts do exist in social streams mentioning the WWF
(the World Wildlife Fund) organization, which do not criticize it, but the neg-
ative impact of climate change, the danger of extinction suffered by a number
of species, and other sustainability issues. Furthermore, approaches in the litera-
ture of sentiment analysis have emerged in the last few years that aim to identify
sentiment targets within a given text, focusing on entity-level and aspect-level
sentiment analysis detection [37][40][54][85], i.e., they first identify the entities
and events appearing in the text, and then check the sentiment expressed towards
them.
• Sentiments are semantics-dependent: Most of existing approaches to sentiment
analysis in social streams have shown effective when sentiment is explicitly and
unambiguously reflected in text fragments through affective (opinionated) words,
such as “great” as in “I got my new Android phone, what a great device!” or “sad”
as in “so sad, now four Sierra Leonean doctors lost to Ebola.” However, merely
relying on affective words is often insufficient, and in many cases does not lead to
satisfactory sentiment detection results [8][27][61]. Examples of such cases arise
when the sentiment of words differs according to (i) the context in which those
words occur (e.g., “great” conveys a negative connotation in the context “pain”
and positive in the context “smile”), or (ii) the conceptual meaning associated
with the words (e.g., “Ebola” is likely to be negative when its associated con-
cept is “Virus” and likely to be neutral when its associated concept is “River”).
Therefore, ignoring the semantics of words when calculating their sentiment, in
either case, may lead to inaccuracies. Recent research in sentiment analysis is
therefore focusing on investigating the identification and use of contextual and
Sentiment Analysis in Social Streams 17

semantic information to enhance the accuracy of traditional machine learning

[59] and lexicon-based approaches [61].
• Sentiments are domain-dependent: Sentiment is expressed in social streams
within multiple domains. For example, the domain of death is generally more
negative than the domain of birth, although both use common terminology, such
as hospital, family, etc. Sentiment analysis approaches need to establish the sen-
timent of the targeted domain to be able to establish the positivity/negativity of
the posts. It has been observed that current sentiment classifiers trained with data
from one specific domain do indeed fail when applied to a different domain [3].
Similarly, while lexicon-based approaches have a higher tolerance to domain
changes, these approaches do suffer when the vocabulary of the domain under
analysis is not well covered by the available sentiment lexicon. Given the great
variety of topics and domains that constantly emerge in social streams, domain
constraints currently affect the applicability of sentiment analysis approaches.
Research is currently being conducted to adapt to new domains, by automatically
assigning sentiment to terms not previously covered by the lexicons, and by pro-
viding dynamic re-training of existing classifiers [9][50][61][65]. There are also
recent approaches aimed to generate domain-dependent lexicons, such as that
presented in [25]. In that work, automatic lexicons17 with emotional categories
for the movie, music and book domains –e.g., gloomy movies, nostalgic music
compositions, and suspenseful books– are automatically generated and modeled
by exploiting information available in social tagging systems and online thesauri.
The terms of these lexicons are also linked to a core lexicon which is composed
of weighted terms associated to 16 general emotions –e.g., happiness, calmness,
and tension– of the well-known Russell’s circumplex model of affect [58].
• Sentiments are language- and culture-dependent: An important problem when
analyzing sentiment in social media streams is that posts are written in different
languages. Even individual posts may include terminology from a variety of lan-
guages within them. Language identification tools are therefore needed to detect
the language in which posts are written [11]. An even more complex problem is
that sentiment is culturally dependent. The way in which we express positivity or
negativity, humor, irony or sarcasm varies depending on our cultural background
[22]. Sentiment analysis tools therefore need to account for language and culture
variances to provide accurate sentiment identification. Few research works have
been recently conducted in this vein, focusing mainly on demographic language
variations (e.g., age, gender) of users to improve sentiment analysis performance
[79, 74].
• Sentiments are personality-dependent: The relationships between emotional states
and personality have been a topic of study in psychology in the last twenty years
(see e.g. seminal works as [55]). The reader can find more details on this in
Chapter ??. In particular, several studies have revealed associations between ex-
traversion and neuroticism (sometimes referred as emotional stability) personal-
ity traits with individual differences in affective level and environmental response

17 [Link]
18 Hassan Saif, F. Javier Ortega, Miriam Fernández, Iván Cantador

[14][55]. This, together with the facts that (i) it has been shown that there exist
correlations between user personality traits and user preferences in several do-
mains [26], and that (ii) approaches have been proposed to infer user personality
from data about user activity and behavior in social streams [2] (see Chapter ??),
raise new research opportunities and applications –such as customer character-
ization, market segmentation, and personalized recommendation– for sentiment
analysis in the context of the Social Web.

References

1. Agrawal, S., Siddiqui, T. J.: Using Syntactic and Contextual Information for Sentiment Po-
larity Analysis. In: Proceedings of the 2nd International Conference on Interaction Sciences
Information Technology, Culture and Human (ICIS’09), pp. 620–623 (2009)
2. Amichai-Hamburger, Y., Vinitzkyb, G.: Social Network Use and Personality. Computers in
Human Behavior 26(6), pp. 1289–1295.
3. Aue, A., Gamon, M.: Customizing Sentiment Classifiers to New Domains: A Case Study. In:
Proceedings of the 3rd International Conference on Recent Advances in Natural Language
Processing (RANLP’05) (2005)
4. Baccianella, S., Esuli, A., Sebastiani, F.: entiWordNet 3.0: An Enhanced Lexical Resource for
Sentiment Analysis and Opinion Mining. In: Proceedings of the 7th International Conference
on Language Resources and Evaluation (LREC’10) (2010)
5. Bentivogli, L., Forner, P., Magnini, B., Pianta, E.: Revising WordNet Domains Hierarchy: Se-
mantics, Coverage, and Balancing. In: Proceedings of the COLLING’04 Workshop on Multi-
lingual Linguistic Resources (MLR’04), pp. 101–108 (2004)
6. Bhuiyan, S. I.: Social Media and its Effectiveness in the Political Reform Movement in Egypt.
Middle East Media Educator 1(1), pp. 14–20 (2011)
7. Bifet, A., Frank, E.: Sentiment Knowledge Discovery in Twitter Streaming Data. In: Proceed-
ings of the 13th International Conference on Discovery Science (DS’10), pp. 1–15 (2010)
8. Cambria, E., Schuller, B., Xia, Y., Havasi, C.: New Avenues in Opinion Mining and Sentiment
Analysis. IEEE Intelligent Systems 28(2), pp. 15–21 (2013)
9. Cambria, E., Song, Y., Wang, H., Howard, N.: Semantic Multi-Dimensional Scaling for Open-
domain Sentiment Analysis. IEEE Intelligent Systems 29(2), pp. 44–51 (2013)
10. Cantador, I., Konstas, I., Jose, J. M. Categorising Social Tags to Improve Folksonomy-based
Recommendations. textitJournal of Web Semantics 9(1), pp. 1–15 (2010)
11. Carter, S., Weerkamp, W., Tsagkias, M. Microblog Language Identification: Overcoming
the Limitations of Short, Unedited and Idiomatic Text. Language Resources and Evaluation
47(1), pp. 195–215 (2013)
12. Carvalho, P., Sarmento, L., Silva, M. J., de Oliveira, E.: Clues for Detecting Irony in User-
generated Contents: Oh...!! It’s ”so easy” ;-) In: Proceedings of the 1st International Work-
shop on Topic-sentiment Analysis for Mass Opinion (TSA’09), pp. 53–56 (2009)
13. Chow, A., Foo, M.-H. N., Manai, G.: HybridRank : A Hybrid Content-Based Approach To
Mobile Game Recommendations. In: Proceedings of the 1st Workshop on New Trends in
Content-based Recommender Systems (CBRecSys’14), pp. 1–4 (2014)
14. Corr, P. J.: The Reinforcement Sensitivity Theory. In: Corr, P. J. (Ed.), The Reinforcement
Senitivity Theory of Personality. Cambridge University Press (2008)
15. Cruz, F. L., Vallejo, C. G., Enrı́quez, F., Troyano, J. A.: PolarityRank: Finding an Equilibrium
between Followers and Contraries in a Network. Information Processing and Management
48(2), pp. 271–282 (2012)
16. Cruz, F. L., Troyano, J. A., Enrı́quez, F., Ortega, F. J., Vallejo, C. G.: Long Autonomy or
Long Delay? The Importance of Domain in Opinion Mining. Expert Systems and Applications
40(8), pp. 3174–3184 (2013)
Sentiment Analysis in Social Streams 19

17. Cruz, F. L., Troyano, J. A., Pontes, B., Ortega, F. J.: Building Layered, Multilingual Sentiment
Lexicons at Synset and Lemma Levels. Expert Systems and Applications 41(13), pp. 5984–
5994 (2014)
18. Davidov, D., Tsur, O., Rappoport, A.: Semi-supervised Recognition of Sarcastic Sentences
in Twitter and Amazon. In: Proceedings of the 14th Conference on Computational Natural
Language Learning (CoNLL’10), pp. 107-116 (2010)
19. Dehkharghani, R., Yanikoglu, B., Tapucu, D., Saygin, Y.: Adaptation and Use of Subjectivity
Lexicons for Domain Dependent Sentiment Classification. In: Proceedings of the 12th IEEE
International Conference on Data Mining Workshops, pp. 669–673 (2012)
20. Barbagallo, D., Bruni, L., Francalanci, C., Giacomazzi, P.: An Empirical Study on the Rela-
tionship between Twitter Sentiment and Influence in the Tourism Domain. Information and
Communication Technologies in Tourism, pp. 506–516 (2012)
21. Durant, K. T., Smith, M. D. Mining Sentiment Classification from Political Web Logs. In:
Proceedings of the WebKDD’06 Workshop on Web Mining and Web Usage Analysis (2006)
22. Elahi, M. F., Monachesi, P.: An Examination of Cross-Cultural Similarities and Differences
from Social Media Data with respect to Language Use. In: Proceedings of the 8th Interna-
tional Conference on Language Resources and Evaluation (LREC’12), pp. 4080–4086 (2012)
23. Feng, Y., Zhuang, Y., Pan, Y.: Music Information Retrieval by Detecting Mood via Computa-
tional Media Aesthetics. In: Proceedings of the 2003 IEEE/WIC International Conference on
Web Intelligence (WI’03), pp. 235–241 (2003)
24. Fernández, M., Allen, B., Wandhoefer, T., Cano, E., Alani, H.: Using Social Media To Inform
Policy Making: To Whom are we Listening? In: Proceedings of the 1st European Conference
on Social Media (ECSM’14), pp. 174–182 (2014)
25. Fernández-Tobı́as, I., Cantador, I., Plaza, L.: An Emotion Dimensional Model Based on So-
cial Tags: Crossing Folksonomies and Enhancing Recommendations. In: Proceedings of the
14th International Conference on E-Commerce and Web Technologies (EC-Web’13), pp. 88–
100 (2013)
26. Fernández-Tobı́as, I., Cantador, I.: Personality-Aware Collaborative Filtering: An Empirical
Study in Multiple Domains with Facebook Data. In: Proceedings of the 15th International
Conference on E-Commerce and Web Technologies (EC-Web’14), pp. 125–137 (2013)
27. Gangemi, A., Presutti, V., Reforgiato Recupero, D.: Frame-based Detection of Opinion Hold-
ers and Topics: A Model and a Tool. IEEE Computational Intelligence Magazine 9(1), pp.
20–30 (2014)
28. Hancock, J. T., Cardie, C.: Finding Deceptive Opinion Spam by Any Stretch of the Imag-
ination. In: Proceedings of the 49th Annual Meeting of the Association for Computational
Linguistics (HLT’11), pp. 309–319 (2011)
29. Hatzivassiloglou, V., McKeown, K. R.: Predicting the Semantic Orientation of Adjectives.
In: Proceedings of the 35th Annual Meeting on Association for Computational Linguistics
(ACL’98), pp. 174–181 (1998)
30. Hu, M., Liu, B.: Mining and Summarizing Customer Reviews. In: Proceedings of the
2004 ACM SIGKDD International Conference on Knowledge Discovery and Data Mining
(KDD’04), pp. 168–177 (2004)
31. Hu, M., Liu, B.: Opinion Feature Extraction Using Class Sequential Rules. In: Proceeings of
the AAAI’06 Spring Symposium: Computational Approaches (2006)
32. Jia, L., Yu, C., Meng, W.: The Effect of Negation on Sentiment Analysis and Retrieval Ef-
fectiveness. In: Proceedings of the 18th ACM Conference on Information and Knowledge
Management (CIKM’10), pp. 1827–1830 (2010)
33. Jindal, N., Liu, B.: Opinion Spam and Analysis. In: Proceedings of the 2008 International
Conference on Web Search and Data Mining (WSDM’08), pp. 219–230 (2008)
34. Kamps, J., Marx, M., Mokken, R. J., Rijke, M.: Using WordNet to Measure Semantic Ori-
entations of Adjectives. In: Proceedings of the 4th International Conference on Language
Resources and Evaluation (LREC’04), pp. 1115–1118 (2004)
35. Kaplan, A. M., Haenlein, M.: Users of the World, Unite! The Challenges and Opportunities
of Social Media. Business Horizons 53(1), pp. 59–68 (2010)
20 Hassan Saif, F. Javier Ortega, Miriam Fernández, Iván Cantador

36. Liu, B.: Web Data Mining: Exploring Hyperlinks, Contents, and Usage Data (2nd edition).
Springer (2011)
37. Long, J., Yu, M., Zhou, M., Liu, X., Zhao, T.: Target-dependent Twitter Sentiment Classi-
fication. In: Proceedings of the 49th Annual Meeting of the Association for Computational
Linguistics: Human Language Technologies (HLT’11), pp. 151–160 (2011)
38. Maynard, D., Bontcheva, K., Rout, D.: Challenges in Developing Opinion Mining Tools for
Social Media. In: Proceedings of NLP can u tag# usergeneratedcontent?! Workshop (2012)
39. Maynard, D., Gossen, G., Funk, A., Fisichella, M.: Should I Care about Your Opinion? De-
tection of Opinion Interestingness and Dynamics in Social Media. Future Internet 6(3), pp.
457–481 (2014)
40. Meng, X., Wei, F., Liu, X., Zhou, M., Li, S., Wang, H.: Entity-centric Topic-oriented Opinion
Summarization in Twitter. In: Proceedings of the 18th ACM SIGKDD International Confer-
ence on Knowledge Discovery and Data Mining (KDD’12), pp. 379–387 (2012)
41. Mihalcea, R., Strapparava, C.: Making Computers Laugh. In: Proceedings of the 2005 Con-
ference on Human Language Technology and Empirical Methods in Natural Language Pro-
cessing (HLT’05), pp. 531–538 (2005)
42. Miller, G.A.: WordNet: a Lexical Database for English. Communications of the ACM 38(11),
pp. 39–41 (1995)
43. Miller, L., Williamson, A.: Digital Dialogs - Third Phase Report. Handsard Society (2008)
44. Morinaga, S., Yamanishi, K., Tateishi, K., Fukushima, T.: Mining Product Reputations on
the Web. In: Proceedings of the 8th ACM SIGKDD International Conference on Knowledge
Discovery and Data Mining (KDD’02), pp. 341–349 (2002)
45. O’Connor, B., Balasubramanyan, R., Routledge, B. R., Smith, N. A.: From Tweets to Polls:
Linking Text Sentiment to Public Opinion Time Series. In: Proceedings of the 4th Interna-
tional AAAI Conference on Weblogs and Social Media (ICWSM’10), pp. 122–129. (2010)
46. Ortega, F. J.: Detection of Dishonest Behaviors in On-line Networks using Graph-based Rank-
ing Techniques. AI Communications 26(3), pp. 327–329 (2013)
47. Ott, M., Cardie, C., Hancock, J. T.: Negative Deceptive Opinion Spam. In: Proceedings of
2013 Conference of the North American Chapter of the Association for Computational Lin-
guistics (NAACL-HLT’13), pp. 497–501 (2013)
48. Pang, B., Lee, L.: Opinion Mining and Sentiment Analysis. Foundations and Trends in Infor-
mation Retrieval 2(1-2), pp. 1–135 (2008)
49. Pak, A., Paroubek, P. Twitter as a Corpus for Sentiment Analysis and Opinion Mining. In:
Proceedings of the 5th International Conference on Language Resources and Evaluation
(LREC’10), pp. 1320–1326 (2010)
50. Peddinti, V. M. K., Chintalapoodi, P.: Domain Adaptation in Sentiment Analysis of Twitter.
Analyzing Microtext, vol. WS-11-05 of AAAI’11 Workshops (2011)
51. Pérez-Rosas, V., Banea, C., Mihalcea, R.: Learning Sentiment Lexicons in Spanish. In:
Proceedings of the 8th International Conference on Language Resources and Evaluation
(LREC’12), pp. 3077–3081 (2012)
52. Popescu, A.-M., Etzioni, O.: Extracting Product Features and Opinions from Reviews. In:
Proceedings of the Conference on Human Language Technology and Empirical Methods in
Natural Language Processing (HLT/EMNLP’05), pp. 339–346 (2005)
53. Qiu, G., Liu, B., Bu, J., Chen, C.: Opinion Word Expansion and Target Extraction through
Double Propagation. Computational Linguistics 37(1), pp. 9–27 (2011)
54. Recupero, D. R., Presutti, V., Consoli, S., Gangemi, A., Nuzzolese, A. G. Sentilo: Frame-
based Sentiment Analysis. Cognitive Computation, September 2014, pp. 1–15 (2014)
55. Revelle, W.: Personality Processes. Annual Review of Psychology 46, pp. 295–328 (1995)
56. Reyes, A., Rosso, P., Buscaldi, D.: From Humor Recognition to Irony Detection: The Figura-
tive Language of Social Media. Data & Knowledge Engineering 74, pp. 1–12 (2012)
57. Riloff, E., Wiebe, J., Wilson, T. Learning Subjective Nouns Using Extraction Pattern Boot-
strapping. In: Proceedings of the 7th Conference on Computational Natural Language Learn-
ing (CoNLL’03), vol. 4., pp. 25–32 (2003)
58. Russell, J. A.: A Circumplex Model of Affect. Journal of Personality and Social Psychology
39(6), pp. 1161–1178 (1980)
Sentiment Analysis in Social Streams 21

59. Saif, H., He, Y., Alani, H. Semantic Sentiment Analysis of Twitter. In: Proceedings of the
11th International Semantic Web Conference (ISWC’12), pp. 508–524 (2012)
60. Saif, H., He, Y., Alani, H.: Alleviating Data Sparsity for Twitter Sentiment Analysis. In:
Proceedings of the WWW’12 Workshop on Making Sense of Microposts (2012)
61. Saif, H., Fernández, M., He, Y., Alani, H.: SentiCircles for Contextual and Conceptual Se-
mantic Sentiment Analysis of Twitter. In: Proceedings of the 11th Extended Semantic Web
Conference (ESWC’14), pp. 83–98 (2014)
62. Saif, H., Fernández, M., He, Y., Alani, H.: On Stopwords, Filtering and Data Sparsity for Sen-
timent Analysis of Twitter. In: Proceedings of the 9th International Conference on Language
Resources and Evaluation (LREC’14), pp. 810–817 (2014)
63. Saif, H., He, Y., Fernández, M., Alani, H.: Semantic Patterns for Sentiment Analysis of Twit-
ter. In: Proceedings of the 13th International Semantic Web Conference (ISWC’14) - part 2,
pp. 324–340 (2014)
64. Sebastiani, F., Esuli, A.: Determining Term Subjectivity and Term Orientation for Opinion
Mining. In: Proceedings of the 11th Conference of the European Chapter of the Association
for Computational Linguistics (EACL’06) (2006)
65. Silva, I. S., Gomide, J., Veloso, A., Meira Jr, W., Ferreira, R.: Effective Sentiment Stream
Analysis with Self-augmenting Training and Demand-driven Projection. In: Proceedings of
the 34th international ACM SIGIR Conference on Research and Development in Information
Retrieval (SIGIR’11), pp. 475–484 (2011)
66. Simon, T., Goldberg, A., Aharonson-Daniel, L., Leykin, D., Adini, B.: Twitter in the Cross
Fire – The Use of Social Media in the Westgate Mall Terror Attack in Kenya. PloS one 9(8):
e104136 (2014)
67. Strapparava, C., Valitutti, A.: Wordnet-affect: An Affective Extension of WordNet. In:
Proceedings of the 4th International Conference on Language Resources and Evaluation
(LREC’04), pp. 1083–1086 (2004)
68. Strapparava, C., Mihalcea, R.: Learning to Identify Emotions in Text. In: Proceedings of the
2008 ACM Symposium on Applied Computing (SAC’08), pp. 1556–1560 (2008)
69. Stone, P. J., Dunphy, D. C., Smith, M. S.: The General Inquirer: A Computer Approach to
Content Analysis. MIT Press (1966)
70. Szomszor, M., Cantador, I., Alani, H.: Correlating User Pprofiles from Multiple Folk-
sonomies. In: Proceedings of the 19th ACM Conference on Hypertext and Hypermedia (Hy-
pertext’08), pp. 33–42 (2008)
71. Taboada, M., Brooke, J., Tofiloski, M., Voll, K., Stede, M.: Lexicon-Based Methods for Sen-
timent Analysis. Computational Linguistics 37(2), pp. 267–307 (2011)
72. Tkalcic, M., Burnik, U., Odic, A., Kosir, A., Tasic, J.: Emotion-Aware Recommender Systems
- A Framework and a Case Study. In: Markovski, S., Gusev, M. (Eds.), ICT Innovations 2012.
Advances in Intelligent Systems and Computing 207, pp. 141–150. Springer (2013)
73. Thelwall, M., Buckley, K., Paltoglou, G., Cai, D., Kappas, A.: Sentiment Strength Detection
in Short Informal Text. Journal of the American Society for Information Science and Tech-
nology 61(12), pp. 2544–2558 (2010)
74. Thelwall, M., Wilkinson, D., & Uppal, S. Data mining emotion in social network commu-
nication: Gender differences in MySpace. Journal of the American Society for Information
Science and Technology 61(1), pp. 190–199 (2010)
75. Thelwall, M., Buckley, K., & Paltoglou, G. Sentiment strength detection for the social web.
Journal of the American Society for Information Science and Technology 63(1), pp. 163–173
(2012)
76. Thomas, K., Fernández, M., Brown, S., Alani, H.: OUSocial2 - A Platform for Gathering
Students’ Feedback from Social Media. Demo at the 13th International Semantic Web Con-
ference (ISWC’14) (2014)
77. Tumasjan, A., Sprenger, T. O., Sandner, P. G., Welpe, I. M.: Predicting Elections with Twitter:
What 140 Characters Reveal about Political Sentiment. In: Proceedings of the 4th Interna-
tional AAAI Conference on Weblogs and Social Media (ICWSM’10), pp. 178–185 (2010)
22 Hassan Saif, F. Javier Ortega, Miriam Fernández, Iván Cantador

78. Turney, P.: Thumbs Up or Thumbs Down? Semantic Orientation Applied to Unsupervised
Classification of Reviews. In Proceedings of the 40th Annual Meeting of the Association for
Computational Linguistics (ACL’02), pp. 417–424 (2002)
79. Volkova, S., Wilson, T., & Yarowsky, D. Exploring Demographic Language Variations to
Improve Multilingual Sentiment Analysis in Social Media. In EMNLP, pp. 1815–1827 (2013)
80. Vorderer, P., Klimmt, C., Ritterfeld, U.: At the Heart of Media Entertainment. Communication
Theory 14(4), pp. 388–08 (2004)
81. Wiebe, J., Bruce, R., O’Hara, T.: Development and Use of a Gold Standard Data Set for
Subjectivity Classifications. In Proceedings of the 37th Annual Meeting of the Association
for Computational Linguistics (ACL’99), pp. 246–253 (1999)
82. Wiebe, J., Wilson, T., Cardie, C.: Annotating Expressions of Opinions and Emotions in Lan-
guage. Language Resources and Evaluation 39(2-3), pp. 165–210 (2006)
83. Wilson, T., Wiebe, J., Hoffmann, P.: Recognizing Contextual Polarity in Phrase-Level Senti-
ment Analysis. In: Proceedings of the 2005 Conference on Human Language Technology and
Empirical Methods in Natural Language Processing (HLT’05), pp. 347–354 (2005)
84. Wilson, T., Wiebe, J., Hoffmann, P.: Recognizing Contextual Polarity: An Exploration of
Features for Phrase-Level Sentiment Analysis. Computational Linguistics 35(3), pp. 399–433
(2009)
85. Yerva, S. R., Mikls, Z. Aberer, K.: Entity-based Classification of Twitter Messages. Interna-
tional Journal of Computer Science and Applications 9, pp. 88–115 (2012)
86. Yu, H., Hatzivassiloglou, V.: Towards Answering Opinion Questions: Separating Facts from
Opinions and Identifying the Polarity of Opinion Sentences. In: Proceedings of the 2003
Conference on Empirical Methods in Natural Language Processing (EMNLP’03), pp. 129–
136 (2003)
87. Zhang, J., Tang, J., Li, J.: Expert Finding in a Social Network. In: Proceedings of the 12th
International Conference on Database Systems for Advanced Applications (DASFAA’07), pp.
1066–1069 (2007)
88. Zillmann, D.: Mood Management: Using Entertainment to Full Advantage. In: Donohew, L.,
Sypher, H. E., Higgins, E. T. (Eds.), Communication, Social Cognition, and Affect, pp. 147–
171. Lawrence Erlbaum Associates (1988)