Mishra defends dissertation

Shubhanshu Mishra
Shubhanshu Mishra

Doctoral candidate Shubhanshu Mishra successfully defended his dissertation, "Information Extraction from Digital Social Trace Data with Applications to Social Media and Scholarly Communication Data," on June 24.

His committee included Associate Professor Jana Diesner, chair and director of research; Associate Professor Vetle Torvik; Karrie Karahalios, iSchool affiliate and professor of computer science; and Robert J. Brunner, professor of accountancy.

From the abstract:  Information extraction aims at developing structured data from an unstructured or semi-structured data set. The thesis starts by identifying social media data and scholarly communication data as a special case of digital social trace data (DSTD). This identification allows us to utilize the graph structure of the data (e.g. user connected to a tweet, author connected to a paper, author connected to authors, etc.) for developing new information extraction tasks. The thesis focuses on information extraction from DSTD, first using only the text data from tweets and scholarly paper abstracts, and then using the full graph structure of Twitter and scholarly communications corpora. This thesis makes three major contributions. First, methods are introduced for extracting information from social media and scholarly data. Second, new categories of information extraction are introduced. Finally, this thesis has resulted in the creation of multiple open source tools and public data sets, which can be utilized by the research community. 
 

Updated on
Backto the news archive

Related News

Get to know Laura Fruhauff, MS student and scholarship recipient

Leep student Laura Fruhauff was on the verge of emailing her advisor to rescind her fall 2019 registration when she received notification from the iSchool that she would be receiving the Helen T. Stewart and Mildred Stewart Scholarship. During her undergraduate studies at Roosevelt University in Chicago, she sometimes worked 80 hours a week to stay in school. According to Fruhauff, “This time around, in graduate school, I cannot do that. In addition to my full-time job, I have caretaker responsibilities to my parents and to my partner that occupy those other hours and funds I had originally designated to school. I cannot impress enough how crucial receiving a scholarship was and is for me and how grateful I am.”
 

Laura Fruhauff

Stodden to present reproducibility research at AAAS Annual Meeting

Associate Professor Victoria Stodden will present her reproducibility research at the American Association for the Advancement of Science (AAAS) Annual Meeting, which is billed as the world's largest general scientific gathering. The 2020 meeting, with the theme "Envisioning Tomorrow’s Earth," will take place on February 13-16 in Seattle, Washington.

Victoria Stodden

He research group to present at artificial intelligence conference

Members of Associate Professor Jingrui He's research group, the iSAIL Lab, will present a paper and tutorial at the thirty-fourth Association for the Advancement of Artificial Intelligence (AAAI) Conference, which will take place on February 7-12 in New York. The AAAI meeting is one of the world's leading conferences in the field of artificial intelligence (AI). The event promotes research in artificial intelligence and scientific exchange among researchers, practitioners, scientists, and engineers in affiliated disciplines.

Jingrui He

Internship Spotlight: Airbnb

PhD student Natã Barbosa worked as an intern at Airbnb in summer 2019. The internship provided the basis for his paper, "Designing for Trust: A Behavioral Framework for Sharing Economy Platforms," which was selected for The Web Conference 2020. Barbosa was recently named a 2020 Facebook Fellowship finalist.

Nata Barbosa

Webcast on reproducibility to feature Stodden

Associate Professor Victoria Stodden will present the webcast, "Community Efforts Advancing Reproducibility and Transparency in Data- and Computationally-Enabled Research," on February 7. Her talk is part of a nine-week series of webcasts hosted by Project TIER (Teaching Integrity in Empirical Research), in which leaders in research transparency discuss their latest thinking on how to make statistical research open, reproducible, and credible. Registration for the webcast, which will take place at 12:00 p.m., is free but required to access the live stream.

Victoria Stodden