Collaborating Authors


AAAI Conferences

Social media has become prominently popular. Tens of millions of users login to social media sites like Twitter to disseminate breaking news and share their opinions and thoughts. For businesses, social media is potentially useful for monitoring the public perception and the social reputation of companies and products. Despite great potential, how bad news about a company influences the public sentiments in social media has not been studied in depth. The aim of this study is to assess people's sentiments in Twitter upon the spread of two types of information: corporate bad news and a CEO's apology.

Why automated sentiment analysis is broken and how to fix it


One of the most difficult challenges reporting and analytics face in public relations measurement is sentiment analysis. Machines attempt textual analysis of sentiment all the time; more often than not, it goes horribly wrong. How does it go wrong? Machines are incapable of understanding context. Machines are typically programmed to look for certain keywords as proxies for sentiment.

Domain-Specific Sentiment Classification for Games-Related Tweets

AAAI Conferences

Sentiment classification provides information about the author's feeling toward a topic through the use of expressive words. However, words indicative of a particular sentiment class can be domain-specific. We train a text classifier for Twitter data related to games using labels inferred from emoticons. Our classifier is able to differentiate between positive and negative sentiment tweets labeled by emoticons with 75.1% accuracy. Additionally, we test the classifier on human-labeled examples with the additional case of neutral or ambiguous sentiment. Finally, we have made the data available to the community for further use and analysis.

Modelling Individual Negative Emotion Spreading Process with Mobile Phones

AAAI Conferences

Individual mood is important for physical and emotional well-being, creativity and working memory. However, due to the lack of long-term real tracking daily data in individual level, most current works focus their efforts on population level and short-term small group. An ignored yet important task is to find the sentiment spreading mechanism in individual level from their daily behavior data. This paper studies this task by raising the following fundamental and summarization question, being not sufficiently answered by the literature so far:Given a social network, how the sentiment spread? The current individual-level network spreading models always assume one can infect others only when he/she has been infected. Considering the negative emotion spreading characters in individual level, we loose this assumption, and give an individual negative emotion spreading model. In this paper, we propose a Graph-Coupled Hidden Markov Sentiment Model for modeling the propagation of infectious negative sentiment locally within a social network. Taking the MIT Social Evolution dataset as an example, the experimental results verify the efficacy of our techniques on real-world data.