Inferring Spread of Readers’ Emotion Affected by Online News
Speaker (s): 
Agus SULISTYA
PhD Candidate
School of Information Systems
Singapore Management University | Date:
Time:
Venue:
| | September 8, 2017, Friday
3:00pm - 3:30pm
Meeting Room 5.1, Level 5
School of Information Systems
Singapore Management University
80 Stamford Road
Singapore 178902
We look forward to seeing you at this research seminar. ![]()
|
|
About the Talk
Depending on the reader, a news article may be viewed from many different perspectives, thus triggering different (and possibly contradicting) emotions. In this paper, we formulate a problem of predicting reader's emotion distribution affected by a news article. Our approach analyzes affective annotation provided by readers of news articles taken from a non-English online news site. We create a new corpus from the annotated articles, and build a domain-specific emotion lexicon and word embedding features. We finally construct a multi-target regression model based on different combination of features. Our experiments show that by combining lexicon and word embedding features, our regression model is able to predict the emotion distribution with RMSE scores between 0.067 to 0.232 for each emotion category.
This is a pre-conference talk for the 9th International Conference on Social Informatics (SocInfo 2017).
About the Speaker
Agus SULISTYA is currently a fourth-year PhD candidate in the School of Information Systems, SMU, under supervision of Associate Professor David Lo and Professor Lim Ee-Peng. Agus’ research focuses on mining and understanding customer feedback using data mining and machine learning.
