Tom Davidson, Sociologist





About me

I’m a PhD candidate in the Department of Sociology at Cornell University. I'm supervised by Mabel Berezin, Filiz Garip, and Michael Macy (chair). I’m also member of the Social Dynamics Lab. I study politics, culture, and social structures using computational methods including social network analysis, machine learning, and natural language processing. My work has been published or is forthcoming in venues including Social Forces, Mobilization, Socius, and ICWSM. You can find out more about my dissertation and other areas of interest below.


Dissertation: Social media and the mainstreaming of the radical right

I am working on a dissertation studying how radical right populist social movements and parties have used social media to organize and interact. I focus on the United Kingdom, which has experienced an upsurge in radical right activities in recent years, including the anti-Muslim Britain First movement and the Euroskeptic UK Independence Party. These groups have managed to break into the political mainstream, shaping the national politics in the era of Brexit, and dominating social media discussions.

I aim to understand why the far-right appears to have been particularly successful at using social media technologies and to what extent this online presence has enabled them to influence other social media users and mainstream politics. I collected data on millions of Facebook posts and engagements with these posts over time, and use a range of techniques to address these questions including social network analysis, natural language processing, and machine learning. My first article based on this work, co-authored with Mabel Berezin, was recently published in Mobilization. My main focus has been the UK, but I am also interested in these trends more broadly, I have co-authored articles in the Washington Post's The Monkey Cage blog on the 2017 German election and the 2018 Italian election, in both cases demonstrating how radical right breakthroughs were associated with dominance on social media.

Computational social science

In addition to my substantive interests, I am also interested in how new methodological developments can be used by sociologists more broadly. In particular, I have focused on studying how machine learning techniques and modes of analysis can be imported from computer science into sociology. In a forthcoming paper in Socius (SocArxiv pre-print) I examine how neural networks can enable us to predict social outcomes and assess the extent to which these black box predictive models can be amenable to sociological explanations. I find that these methods do not appear to radically outperform traditional approaches like linear regression but they appear to inductively use important variables that have been identified in prior sociological research. You can find a pre-print of the paper on Socarxiv. I am currently working on another project with Mario Molina using simulations to examine the relationships between the model-fit statistics typically used by computer scientists and the explanatory statistics used by sociologists.

Social networks

My interest in relational approaches to the study of social life has also led to a number of different projects spanning diverse topics. I collaborated with Paromita Sanyal at FSU to study the impact of microcredit participation on women's social networks in rural India. We find that participation in associations allows women to expand their personal networks and enhance their social capital. Our work was published in Social Forces. I am currently working on a project with my colleague Antonio Sirianni to study the career trajectories of adult film performers and another solo-authored project to study how co-performance and co-production shape the development of musical genres.

Hate speech

I have also collaborated on a number of papers focused on identifying and understanding hate speech and hate speakers on social media using natural language processing and machine learning. You can read our ICWSM paper on automated hate speech detection here and download our data and model here. Our work has been covered in Wired Magazine, Tech Republic, and New Scientist. We also wrote a paper focusing on the commonalities between hate speech detection and other topics, including online abuse and cyberbullying, for the Association for Computational Linguistics 1st Workshop of Abusive Language Online. You can read the article in the workshop proceedings.

Data science

In addition to my academic research I have also been learning about how data science can be used to directly address real world problems in the public sphere and in industry.

In the summer of 2016 I was an Eric and Wendy Schmidt Data Science for Social Good Fellow at the University of Chicago. I worked on a project using machine learning to improve an early-warning system to identify police misconduct and helped develop a new model to predict risks at the dispatch level. You can read about our work here, along with media coverage in The Chicago Tribune, NPR, Mother Jones, the Economist, and Forbes. As of spring 2017 our system is being implemented into two police departments, you can read about the progress here.

In 2017 I was worked as a summer intern in the Data Science Research & Development department at Civis Analytics in Chicago, where I used natural language processing and and machine learning to help build a tool to monitor political discussion on Twitter. In summer 2018 I was a Core Data Science intern at Facebook in Menlo Park. I helped to evaluate and deploy new tools to help in their on-going election integrity efforts.


Please feel free to get in touch at trd54 at cornell dot edu.