In this day and age, where the internet has taken control of most people’s lives, social media exists as one of the most powerful platforms to share and voice one’s opinions. The high volume of user-generated content makes a manual analysis of this discourse unviable. Consequently, automatic analysis techniques are needed to extract the opinions expressed in users’ comments, given that these opinions are an implicit parameter of unquestionable interest for a vast section of the society.
Our project aims to automate this task of analysing the reactions on the posts and generate a report based on the outcome.
Viewers of the post are provided a feature to predict the number of likes their comment would yield based on the post and existing comments.
- The user first inputs a text file which is then tokenized.
- The results are then stored in a database.
- As per the choice of the user, the required information is displayed while maintaining a reasonable level of abstraction.
- Furthermore, the post emotion is then calculated and the comments are segregated based on a score.
- User can then input a new comment and predict the number of likes this comment would fetch after observing the trend of the existing comments on the mentioned post.