TagNet: Toward Tag-Based Sentiment Analysis of Large Social Media Data

Hashtags and replies, originally introduced on Twitter, have become the most popular ways to tag short messages in social networks. While the primary uses of these human-labeled metadata are still for message retrieval and clustering, there have been increasing attempts to use them as subject or topic indicators in measuring people's continuous sentiments in large message corpora. However, conducting the analysis for large social media data is still challenging due to the message volume, heterogeneity, and temporal dependence. In this paper, we present TagNet, a novel visualization approach tailored to the tag-based sentiment analysis. TagNet combines traditional tag clouds with an improved node-link diagram to represent the time-varying heterogeneous information with reduced visual clutter. A force model is leveraged to generate layout aesthetics from which the temporal patterns of tags can be easily compared across different subsets of data. It is enhanced by visual encodings for quickly estimating the time-varying sentiment. Interaction tools are provided to improve the scalability for exploring large corpora. An example Twitter corpus illustrates the applicability and usefulness of TagNet.

[1]  Steven Franconeri,et al.  Taking Word Clouds Apart: An Empirical Investigation of the Design Space for Keyword Summaries , 2018, IEEE Transactions on Visualization and Computer Graphics.

[2]  Kathleen M. Carley,et al.  Contextual Sentiment Analysis , 2016, SBP-BRiMS.

[3]  Susan T. Dumais,et al.  PivotPaths: Strolling through Faceted Information Spaces , 2012, IEEE Transactions on Visualization and Computer Graphics.

[4]  Paulo Cortez,et al.  On the Predictability of Stock Market Behavior Using StockTwits Sentiment and Posting Volume , 2013, EPIA.

[5]  Chen Wang,et al.  Dynamic network visualization in 1.5D , 2011, 2011 IEEE Pacific Visualization Symposium.

[6]  Emden R. GansnerYifan Multilevel Agglomerative Edge Bundling for Visualizing Large Graphs , 2011 .

[7]  Mohammed J. Zaki,et al.  Characterizing the effectiveness of twitter hashtags to detect and track online population sentiment , 2012, CHI Extended Abstracts.

[8]  Bernard J. Jansen,et al.  Micro-blogging as online word of mouth branding , 2009, CHI Extended Abstracts.

[9]  Eva Zangerle,et al.  On the impact of text similarity functions on hashtag recommendations in microblogging environments , 2013, Social Network Analysis and Mining.

[10]  Xiaolong Wang,et al.  Topic sentiment analysis in twitter: a graph-based hashtag sentiment classification approach , 2011, CIKM '11.

[11]  Yee Whye Teh,et al.  Sharing Clusters among Related Groups: Hierarchical Dirichlet Processes , 2004, NIPS.

[12]  C. D. Gelatt,et al.  Optimization by Simulated Annealing , 1983, Science.

[13]  G. W. Furnas,et al.  Generalized fisheye views , 1986, CHI '86.

[14]  Baining Guo,et al.  How ideas flow across multiple social groups , 2016, 2016 IEEE Conference on Visual Analytics Science and Technology (VAST).

[15]  Hansjörg Schmauder,et al.  Visual analysis of microblog content using time-varying co-occurrence highlighting in tag clouds , 2012, AVI.

[16]  Pat Hanrahan,et al.  Multiscale visualization using data cubes , 2002, IEEE Symposium on Information Visualization, 2002. INFOVIS 2002..

[17]  Siddharth Batra,et al.  Entity Based Sentiment Analysis on Twitter , 2010 .

[18]  Martin Wattenberg,et al.  Parallel Tag Clouds to explore and analyze faceted text corpora , 2009, 2009 IEEE Symposium on Visual Analytics Science and Technology.

[19]  M. Sheelagh T. Carpendale,et al.  SparkClouds: Visualizing Trends in Tag Clouds , 2010, IEEE Transactions on Visualization and Computer Graphics.

[20]  David A. Shamma,et al.  Characterizing debate performance via aggregated twitter sentiment , 2010, CHI.

[21]  Finn Årup Nielsen,et al.  A New ANEW: Evaluation of a Word List for Sentiment Analysis in Microblogs , 2011, #MSM.

[22]  Ross Maciejewski,et al.  Understanding Twitter data with TweetXplorer , 2013, KDD.