Sentiment Analysis Sentiment analysis is a natural language processing technique used to determine whether data is positive, negative or neutral. It determines whether a piece of writing is positive, negative or neutral Sentiment analysis is often performed on textual data to help businesses monitor brand and product sentiment in customer feedback, and understand customer needs.
To perform Sentiment Analysis on IMdb reviews of Movies by lexicon approach and to identify whether review is positive, negative or neutral.
- To implement an algorithm for automatically classification of text into positive, negative and neutral.
- To study and implement tokenization.
- To study and implement lemmatization.
- To calculate polarity value of review.
- To calculate accuracy of the algorithm
Step 1: Importing the data set
Step 2: Removing single letters and numeric from the reviews
Step 3: Snippet to tag the parts of speech for each review
Step 4: Narrow down each review with only adjectives and verb form
Step 5: Making a list of tuples which has review and its respective class
Step 6: Separating the data set by each class i.e. "Positive", "Negative", "Neutral"
Step 7: Merge the reviews in each class in to three single lists
Step 8: Splitting the words in each list to get the word frequencies
Step 9: Finding the frequencies of the unique words in each class
Step 10: Snippet to set the dictionary size
Step 11: Identifying the similar words for each class in each review
Step 12: Calculating the score of positive, negative and neutral words in each review
Step 13: Predicting the class based on the score
We have presented a Dictionary-based method for extracting sentiment from texts The algorithm provides a clear idea about the importance and working of the Sentiment predictions. It provides accuracy up to 96%
Sentiment analysis is a uniquely powerful tool for businesses that are looking to measure attitudes, feelings and emotions regarding their brand. To date, the majority of sentiment analysis projects have been conducted almost exclusively by companies and brands through the use of social media data, survey responses and other hubs of user-generated content.
The future of sentiment analysis is going to continue to dig deeper, far past the surface of the number of likes, comments and shares, and aim to reach, and truly understand, the significance of social media interactions and what they tell us about the consumers behind the screens. Our project tries to identify the sentiments value of the review classifying it into positive or negative review. Later on we can create GUI interface which make ease the task of classifying the review