User-level sentiment analysis incorporating social networks
By Chenhao Tan, Lillian Lee, Jie Tang, Long Jiang, M. Zhou, Ping Li. Knowledge Discovery and Data Mining, 2011
483 citations recorded by the source corpus.
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.
Subfields: Artificial Intelligence
View Paper: https://www.semanticscholar.org/paper/ad22a4d103510b07f2b9114b371e591c1a09383f
How researchers see this paper
The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.
In Artificial Intelligence
Citations in the corpus
- A survey of sentiment analysis in social media (2018, background): “Tan et al. [117] used social network structures to help sentiment analysis by incorporating link information.”
- Emoticon Smoothed Language Models for Twitter Sentiment Analysis (2012, methodology): “Most recent works include target-dependent SA based on SVM (Jiang et al. 2011), user-level SA based on social networks (Tan et al. 2011), sentiment stream analysis based on association rules (Silva et al. 2011), and real-time SA (Guerra et al. 2011).”
- Exploiting Social Network Structure for Person-to-Person Sentiment Analysis (2014, methodology): “Thomas et al. (2006) and Tan et al. (2011) cap-italize on this insight using an elaboration of the Balance theory reasons about undirected, status theory about directed, triangles.”
- Learning Semantic Representations of Users and Products for Document Level Sentiment Classification (2015, methodology): “Tan et al. (2011) and Hu et al. (2013) utilize usertext and user-user relations for Twitter sentiment analysis.”
- Exploiting social relations for sentiment analysis in microblogging (2013, background): “[36] proposed to improve user-level sentiment analysis of different topics [16] by incorporating social network information.”
- Attributed Network Embedding for Learning in a Dynamic Environment (2017, background): “Also, many real-world applications, such as community detection, sentiment analysis, and social spammer detection [15, 31, 41], have shown signicant improvements by modeling such correlations.”
- Semantic Sentiment Analysis of Twitter (2012, methodology): “First direction is concerned with finding new methods to run such analysis, such as performing sentiment label propagation on Twitter follower graphs [14], and employing social relations for user-level sentiment analysis [15, 5].”
- Like It or Not (2016, background): “Tan et al. [2011] leveraged users’ social relations to address user-level TSA.”
- A Survey of Signed Network Mining in Social Media (2015, background): “We focus on these tasks because these these problems are very general and have applicability to many problems such as sentiment analysis [Tan et al. 2011; Hu et al. 2013].”
- A survey on semi-supervised learning (2019, background): “Node classification in particular can be considered a regular transductive semi-supervised learning task, and is broadly applied to problems in social network analysis and natural language processing (Tan et al. 2011; Yang et al. 2016).”
- Stylistic Variation in Social Media Part-of-Speech Tagging (2018, methodology): “Tan et al. (2011) and Hu et al. (2013) leverage social relations for sentiment analysis by exploiting a factor graph model and the graph Laplacian technique respectively, so that the tweets belonging to social connected users share similar label distributions.”
- Exploring Demographic Language Variations to Improve Multilingual Sentiment Analysis in Social Media (2013, background): “There has also been a considerable amount of work in subjectivity and sentiment analysis over the past decade, including, more recently, in microblogs (Barbosa and Feng, 2010; Bermingham and Smeaton, 2010; Pak and Paroubek, 2010; Bifet and Frank, 2010; Davidov et al., 2010; Li et al., 2010; Kouloump”