User-level sentiment analysis incorporating social networks

Abstract

We show that information about social relationships can be used to improve user-level sentiment analysis. The main motivation behind our approach is that users that are somehow "connected" may be more likely to hold similar opinions; therefore, relationship information can complement what we can extract about a user's viewpoints from their utterances. Employing Twitter as a source for our experimental data, and working within a semi-supervised framework, we propose models that are induced either from the Twitter follower/followee network or from the network in Twitter formed by users referring to each other using "@" mentions. Our transductive learning results reveal that incorporating social-network information can indeed lead to statistically significant sentiment-classification improvements over the performance of an approach based on Support Vector Machines having access only to textual features.

Proceedings of KDD 2011. Poster

Cited by in corpus (12)

• Attributed Network Embedding for Learning in a Dynamic Environment
• A framework for fake review detection in online consumer electronics retailers
• Tripartite Graph Clustering for Dynamic Sentiment Analysis on Social Media
• Overcoming Language Variation in Sentiment Analysis with Social Attention
• A Survey of Signed Network Mining in Social Media
• Literature Survey on Interplay of Topics, Information Diffusion and Connections on Social Networks
• Identifying Users with Opposing Opinions in Twitter Debates
• Toward Socially-Infused Information Extraction: Embedding Authors, Mentions, and Entities
• Mining Online Social Data for Detecting Social Network Mental Disorders
• Measuring Asymmetric Opinions on Online Social Interrelationship with Language and Network Features
• Topic-Level Opinion Influence Model(TOIM): An Investigation Using Tencent Micro-Blogging
• User-level Weibo Recommendation incorporating Social Influence based on Semi-Supervised Algorithm