Sentiment Analysis, Social Media and Subjective Well-Being
Presented by Stefano Iacus, Senior Research Scientist and Director of Data Science and Product Research, The Institute for Quantitative Social Science, Harvard University
Wednesday, November 30
4:00 p.m. ET
AUST 434
After reviewing a few basic concepts of sentiment analysis for social media analysis, we present the iSA algorithm which is an unbiased, statistically and computationally efficient method for the estimation of the aggregated distribution of opinions in a set of textual data. We discuss further the problems related to different types of bias that arise in the analysis of social media data and an attempt to control for it through statistical methods. Finally, we discuss an application of sentiment analysis that aims at extracting expressions of subjective well-being from Twitter data. In this application we show the impact of the recent COVID-19 pandemic on the derived well-being indicators.
Speaker Bio:
Stefano M. Iacus is the Director of Data Science and Product Research at the Institute for Quantitative Social Science, Harvard University. He is working closely with the Dataverse and OpenDP projects and well as with the Data Science Services at IQSS. Iacus started his academic career at the University of Milan (Italy), where he became full professor of statistics in 2015. He founded and directed the Data Science Lab and two master courses in Finance and Economics and Data Science for Economics. In the period 2019-2022, he has also served as officer at the Joint Research Centre of the European Commission, where he led the team that explored the usage of non-traditional data sources in the context of evidence based policy making in migration and demography to support action during crisis periods and to refine preparedness measures. Since 2006, he has had a recurring visiting position at the Graduate School ot Mathematics at the University of Tokyo (Japan) and he co-leads the Yuima project. He has been a member of the R Core Team for the development of the R statistical environment from 1999 till 2014 and is now a member of the R Foundation for Statistical Computing. Iacus’ accomplishments extend beyond academia. During the COVID-19 pandemic, he managed a large-scale business-to-government project for the European Commission, producing insights for policy-making using data from mobile network operators covering most European Union member states. Iacus has published several books, many scientific articles, and a variety of open-source software products in a number of fields including causal inference, sentiment analysis, inference for stochastic processes, computational statistics, and quantitative finance. His work is widely cited across scholarly fields. He has founded two startup companies in the fields of social media analysis and quantitative finance.