Please use this identifier to cite or link to this item: http://dspace.dtu.ac.in:8080/jspui/handle/repository/16731
Title: A SMART DISCUSSION FORUM PLATFORM
Authors: DANISH, MOHD
Keywords: SENTIMENT ANALYSIS
DUMMY DATA
DISCUSSION FORUM
Issue Date: Jul-2019
Series/Report no.: TD-4579;
Abstract: Sentiment Analysis deals with understanding the context of textual data and further forming an opinion based on the piece of text. The Sentiment Analysis further classifies the user’s emotions and opinions in various categories such as positive, negative, or neutral. Applications of Sentiment Analysis in various research areas are quite abundant and clearly visible across the literature. Here in this paper, we also accomplished the application of Sentiment Analysis. To be specific, we developed a discussion forum website that allows a user to post questions, answers, and comments or feedback of their choice along with to like and dislike answers. This discussion forum then automatically performs the Sentiment Analysis on the feedback or comments posted by the users. This performed Sentiment Analysis categorizes the answers written on various topics on discussion forum website and then presents the emotional quotient of people, i.e., whether the users are happy, angry, or sad, etc. with the answers. Therefore, in our discussion forum, we ranked the answers based on the sentiment score and no. of likes and dislikes, which makes our discussion forum unique as compared to other available discussion forums in the market. In order to realize the effectiveness of our work, dummy data entries were made on the discussion forum website in order to cross verify the ranking of answers based on the sentiment score and no. of likes and dislikes.
URI: http://dspace.dtu.ac.in:8080/jspui/handle/repository/16731
Appears in Collections:M.E./M.Tech. Computer Engineering

Files in This Item:
File Description SizeFormat 
a smart discussion forum platform by Mohd Danish as Thesis .pdf2.46 MBAdobe PDFView/Open


Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.