Mishra to discuss sentiment analysis at hypertext and social media conference

Shubhanshu Mishra
Shubhanshu Mishra

Doctoral student Shubhanshu Mishra will present his research at the 29th ACM Conference on Hypertext and Social Media, which will be held July 9-12 in Baltimore, Maryland. The conference will focus on the role of links, linking, hypertext, and hyperlink theory on the web and beyond.

Mishra will give the talk, "Detecting the correlation between sentiment and user-level as well as text-level meta-data from benchmark corpora," which he coauthored with Assistant Professor Jana Diesner. Their study examined whether users with similar Twitter characteristics have similar sentiments and what meta-data features of tweets and users correlate with tweet sentiment. 

From the abstract: We address these two questions by analyzing six popular benchmark datasets where tweets are annotated with sentiment labels. We consider user-level as well as tweet-level meta-data features, and identify patterns and correlations of these feature with the log-odds for sentiment classes. We further strengthen our analysis by replicating this set of experiments on recent tweets from users present in our datasets; finding that most of the patterns are consistent across our analysis. Finally, we use our identified meta-data features as features for a sentiment classification algorithm, which results in around 2% increase in F1 score for sentiment classification, compared to text-only classifiers, along with a significant drop in KL-divergence. These results have potential to improve sentiment analysis applications on social media data.

Mishra has an integrated MS and BS in mathematics and computing from the Indian Institute of Technology Kharagpur. He is interested in the analysis of information generation in social networks such as those in scholarly data and social media websites. His prior projects have included systems for user sentiment profiling, active learning using human-in-the-loop design pattern, and novelty profiling in scholarly data.

Updated on
Backto the news archive

Related News

Visualizing UFO data leads to recognition for iSchool student

MS/IM student Suyash Singh received Honorable Mention in the Data Visualization Competition sponsored by the University of Illinois Library’s Scholarly Commons. The competition provides students with an opportunity to demonstrate their skills in visually communicating information. Winners were announced on October 9 at the Fall 2018 Scholarly Commons Open House.

Suyash Singh

Diesner appointed R.C. Evans Data Analytics Fellow

Associate Professor and PhD Program Director Jana Diesner has been appointed as a 2018-19 R.C. Evans Data Analytics Fellow in the University of Illinois-Deloitte Foundation Center for Business Analytics. Launched in 2016, the Center is part of the Gies College of Business at the Urbana campus.

Assistant Professor Jana Diesner

Jones to present at digital preservation conference

Doctoral candidate Jimi Jones will discuss his dissertation research at the National Digital Stewardship Alliance (NDSA) Digital Preservation 2018, which will be held October 17-18 in Las Vegas. NDSA is a consortium of more than 220 organizations committed to the long-term preservation and stewardship of digital information and cultural heritage, for the benefit of present and future generations.

Jimi Jones

First place win for MS/IM students’ hackathon team

Three iSchool students were on the winning team at PygHack 2018, a 24-hour hackathon that brings together coders, designers, engineers, and dreamers to work together to create something that can benefit the community or an organization in Champaign-Urbana. This year's event was held on September 29-30 at the University of Illinois Research Park. PygHack projects were judged on community benefit, collaboration, design, functioning prototype, and innovation. 

PygHack team