Emotion and Sentiment Analysis from Twitter Text
Date
2018-07-27
Authors
Journal Title
Journal ISSN
Volume Title
Publisher
Abstract
Online social networks have emerged as new platform that provide people an arena to share their views and perspectives on different issues and subjects with their friends, family, and other users. We can share our thoughts, mental states, moments and stances on specific social, and political issues through texts, photos, audio/video messages and posts. Indeed, despite the availability of other forms of communication, text is still one of the most common ways of communication in a social network. Twitter was chosen in this research for data collection, experimentation and analysis. The research described in this thesis is to detect and analyze both sentiment and emotion expressed by people through texts in their Twitter posts. Tweets and replies on few recent topics were collected and a dataset was created with text, user, emotion and sentiment information. The customized dataset had user detail like user ID, user name, user's screen name, location, number of tweets/followers/likes/followees. Similarly, for textual information, tweet ID, tweet time, number of likes/replies/retweets, tweet text, reply text and few other text based data were collected. The texts of the dataset were then annotated with proper emotions and sentiments according to some benchmark models. The customized dataset was then used to detect sentiment and emotion from tweets and their replies using machine learning. The influence scores of users were also calculated based on various user-based and tweet-based parameters. Based on those information, both generalized and personalized recommendations were offered for users based on their Twitter activities.
Description
Keywords
Text Emotion Analysis
Citation
Sailunaz, K. (2018). Emotion and Sentiment Analysis from Twitter Text (Master's thesis, University of Calgary, Calgary, Canada). Retrieved from https://prism.ucalgary.ca. doi:10.11575/PRISM/32714