IC Colloquium: Detecting and combating polarization in online media
Event details
Date | 18.11.2019 |
Hour | 14:15 › 15:30 |
Location | |
Category | Conferences - Seminars |
By: Aristides Gionis - Aalto University
Video of his talk
Abstract:
Online social media is an important venue of public discourse today, hosting the opinions of hundreds of millions of individuals. Social media are often credited for providing a technological means to break information barriers and promote diversity and democracy. In practice, however, the opposite effect is often observed: users tend to favor content that agrees with their existing world-view, get less exposure to conflicting viewpoints, and eventually create "echo chambers" and increased polarization. Arguably, without any kind of moderation, current social-media platforms gravitate towards a state in which net-citizens are constantly reinforcing their existing opinions.
In this talk we present some of our ongoing work on analyzing discussions in online media. We first focus on the problem of detecting polarization in signed networks, which offer a simple but powerful abstraction to model user interactions by annotating edges as positive (friendly) or negative (antagonistic). Detecting polarization in signed networks is formulated as searching for two subsets of vertices (communities) having mostly positive edges within and mostly negative edges across. We distinguish different problem variants, and we develop algorithms with provable guarantees based on spectral analysis. We then address the problem of designing algorithms to break filter bubbles, reduce polarization, and increase diversity. We discuss different strategies based on content recommendation, as well as an approach based on clustering with non-polarized representatives.
Bio:
Aristides Gionis is a professor in the department of Computer Science in Aalto University. He is currently a fellow in the ISI Foundation, Turin, and in 2016 he was a visiting professor in the University of Rome. His previous appointment was with Yahoo! Research, Barcelona, where he was a senior research scientist and group leader. He obtained his PhD in 2003 from Stanford University, USA. He is currently serving as an action editor in the Data Management and Knowledge Discovery journal (DMKD), an associate editor in the ACM Transactions on Knowledge Discovery from Data (TKDD), and an associate editor in the ACM Transactions on the Web (TWEB). He has contributed in different areas of data science, such as algorithmic data analysis, web mining, social-media analysis, data clustering, and privacy-preserving data mining. His current research is funded by the Academy of Finland (projects Nestor, Agra, AIDA, and MLDB) and by the European Commission (project SoBigData).
More information
Video of his talk
Abstract:
Online social media is an important venue of public discourse today, hosting the opinions of hundreds of millions of individuals. Social media are often credited for providing a technological means to break information barriers and promote diversity and democracy. In practice, however, the opposite effect is often observed: users tend to favor content that agrees with their existing world-view, get less exposure to conflicting viewpoints, and eventually create "echo chambers" and increased polarization. Arguably, without any kind of moderation, current social-media platforms gravitate towards a state in which net-citizens are constantly reinforcing their existing opinions.
In this talk we present some of our ongoing work on analyzing discussions in online media. We first focus on the problem of detecting polarization in signed networks, which offer a simple but powerful abstraction to model user interactions by annotating edges as positive (friendly) or negative (antagonistic). Detecting polarization in signed networks is formulated as searching for two subsets of vertices (communities) having mostly positive edges within and mostly negative edges across. We distinguish different problem variants, and we develop algorithms with provable guarantees based on spectral analysis. We then address the problem of designing algorithms to break filter bubbles, reduce polarization, and increase diversity. We discuss different strategies based on content recommendation, as well as an approach based on clustering with non-polarized representatives.
Bio:
Aristides Gionis is a professor in the department of Computer Science in Aalto University. He is currently a fellow in the ISI Foundation, Turin, and in 2016 he was a visiting professor in the University of Rome. His previous appointment was with Yahoo! Research, Barcelona, where he was a senior research scientist and group leader. He obtained his PhD in 2003 from Stanford University, USA. He is currently serving as an action editor in the Data Management and Knowledge Discovery journal (DMKD), an associate editor in the ACM Transactions on Knowledge Discovery from Data (TKDD), and an associate editor in the ACM Transactions on the Web (TWEB). He has contributed in different areas of data science, such as algorithmic data analysis, web mining, social-media analysis, data clustering, and privacy-preserving data mining. His current research is funded by the Academy of Finland (projects Nestor, Agra, AIDA, and MLDB) and by the European Commission (project SoBigData).
More information
Practical information
- General public
- Free
- This event is internal
Contact
- Host: Robert West