Affective analysis of text in tweets

Affective computing is the study and development of devices that can recognize emotions through various modes such as video, audio and text automatically. In this thesis, I focus on the problem of affective computing in short texts, in particular, tweets. With the evolution of social media in the recent years, there has been a rapid growth of interactions that take occur online, which are expressive in terms of emotion. Internet users today have several diverse methods of being expressive through text, such as by using abbreviations, emoticons and hashtags. I use traditional lexical features and word embeddings to extract semantic and lexical information from the input text. I develop models ranging from linear and tree-based models to deep neural networks to perform emotion detection on Tweets. I create an ensemble of these methods to make my final predictions. I evaluate the ensemble on the SemEval 2018 dataset containing intensity and class annotations for emotions in tweets. I finally perform an error analysis of these algorithms and highlight potential areas of improvement.

Name thesis:degree_name

M.S.

Level thesis:degree_level

Thesis

Discipline thesis:degree_discipline

Computer Science

Grantor

University of Illinois at Urbana-Champaign

Year dc:date

2018

Author dc:creator

• Narwekar, Abhishek Avinash

Contributors dc:contributor

• Girju, Roxana

• affective computing, emotion detection, sentiment analysis, text processing, emotion in tweets

Statement dc:rights

• Copyright 2018 Abhishek Avinash Narwekar

Language dc:language

en

Handle dc:identifier

http://hdl.handle.net/2142/101090

OAI identifier oai:identifier

oai:www.ideals.illinois.edu:2142/101090