Scribd
Upload
5 views6 pages

Naive Bayes Sentiment Analysis Results

The document discusses classifying two text samples as positive or negative using naive Bayes classification. It reports the 99.5% accuracy of the classifier on the samples and validates the results by calculating word frequencies and creating a word cloud. Analysis found the samples contained both positive and negative tweets, with the most common words relating to movies. The naive Bayes classifier accurately classified the tweets as positive or negative.

Uploaded by

api-438127639
Copyright
© All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as PDF, TXT or read online on Scribd
5 views6 pages

Naive Bayes Sentiment Analysis Results

The document discusses classifying two text samples as positive or negative using naive Bayes classification. It reports the 99.5% accuracy of the classifier on the samples and validates the results by calculating word frequencies and creating a word cloud. Analysis found the samples contained both positive and negative tweets, with the most common words relating to movies. The naive Bayes classifier accurately classified the tweets as positive or negative.

Uploaded by

api-438127639
Copyright
© All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as PDF, TXT or read online on Scribd

ASSIGNMENT-14

REDDIVARI SAI SARAN


G01142501

1. For each datafile, run the NaiveBayes classifier from the Notebook and report the output whether it is
classified as pos or neg.
2. Validate your answer by calculating Frequency of word count as well as visualizing it using wordcloud.

TEXTSAMPLE1:
TEXTSAMPLE2:
3. Explain your analysis based on your results from question 1 and 2.

The accuracy for the textsample1 and textsample2 is 99.50 when we use naïve Bayes
classification. If you look at the actual data, you'll see that the data is kind of messy there are
typos, abbreviations, grammatical errors of all sorts
The textsample1 and textsample2 contain both pos and neg tweets. The most commonly used
words in textsample1 are love, Vinci, Harry, like, awesome, impossible, mountain, etc. The most
commonly used words in textsample2 are Vinci, harry, mountain, code, hate, sucked, sucks,
movie, etc
The positive and negative tweets used commonly are Vinci, mountain, brokeback, mission, etc.
The naive Bayes classification helped to classify the negative and positive tweets with more
accuracy.

You might also like