The ASA’s Text Analysis Interest Group (TAIG) has had a productive first full year. TAIG brings together individuals and groups who have an active interest in text analysis, text mining, natural language processing, and related areas of research at their intersection with statistics. It works to increase awareness of statistical community in tools and methods of text analysis, promote text analysis as an integral part of modern statistics education, and involve statisticians in research in text analysis.

The group was formed in 2019. In 2020, it had a full slate of officers: Stas Kolenikov (founder and 2020 chair, 2021 past chair), Kelly Zou (2020 chair-elect, 2021 chair), Carol Haney (2020/2021 secretary-treasurer), Jordan Rodu (2020 program chair-elect, 2021 program chair), Tommy Jones (webmaster), and Qiuyi Wu (student representative). The officers met eight times throughout 2020.

At JSM 2020, held virtually, the group had a full program, co-sponsoring a total of 22 sessions. The three sessions devoted entirely to text analysis were the following:

• “Statistics of Social Media” invited session with presentations by Emilio Zagheni and Juha Alho and discussion by Frauke Kreuter
• “Big Data, Technology Platform and Digital Innovation with Measurable Impact” topic-contributed panel organized by Kelly Zou with panelists Siddhartha Dalal, Mike Henderson, Joe Imperato, Stas Kolenikov, Lourenco Miranda, Mike Porath, and May Yamada-Lifton
• “Natural Language Processing Applications in Defense and National Security” topic-contributed session with presentations by Svitlana Volkova, Richard Field, Lauren Phillips, and Kelly Townsend and discussion by David Marchette

The group also held a virtual presentation competition in two categories—student and professional—with the interest group officers serving as judges. The professional category award winner was Enshuo Hsu and team from The University of Texas Medical Branch for their presentation, “Combination of Optical Character Recognition and Natural Language Processing to Identify Patients with Sleep Apnea in EHR Data.” The student category award winner was Qiuyi Wu of the University of Rochester for her presentation, “Naive Dictionary on Musical Corpora: From Knowledge Representation to Pattern Recognition.” Each award was accompanied by a $500 check to the presenting author.

TAIG also held a business meeting and social hour on Zoom on the last day of JSM. The officers talked about official business of the group, and then everyone chatted about the prospects of the group and interesting developments in the text analysis field.

Preparations are underway for JSM 2021. An invited session, titled “Words and Insights via Text Analysis,” was accepted. It is organized by Kelly Zou, with Mike Baiocchi, Mike Henderson, Tommy Jones, and Tian Zheng presenting. A topic-contributed session, “Statistical Approaches in Text Analysis,” is being organized by Jordan Rodu, with Qiuyi Wu, Michael Crotty, Daniel Fortin, and Jordan Rodu presenting. Also planned is a short course on text analysis by Karl Pazdernik.

In the fall of 2020, TAIG held elections for two offices: chair and program chair. David Banks was elected as 2021 chair-elect (2022 chair), and Brandon Sepulvado was elected as the 2021 program chair-elect (2022 program chair).

The group is exploring the possibility of collaborating with other ASA sections, such as the Section on Statistical Computing and Section on Statistical Learning and Data Science, as well as with external organizations. Also, the group has an agreement with Data Science DC for the JSM 2020 presentation award winners to give their talks at their fora.

In 2021, the group plans to offer a webinar to help other statisticians familiarize themselves with text analysis as a research area. For more information about the group or to join, visit the group’s website.