Hello world! ⚡ I am Myrthe Reuver, an NLP researcher specializing in computational argumentation, ethical and responsible use of NLP, and interdisciplinary research - mostly in the connection between NLP and the social and political sciences. I am especially interested in careful evaluation: Are we measuring what we think we are measuring? 🤔 I also enjoy presenting research outcomes to different audiences - whether in talks, papers, or reports.

Currently, I am working as an NLP Engineer and Researcher at Populytics, a spin-off from Delft University of Technology that provides analyses of citizens’ opinions about policy dilemmas, setting up experiments within a carefully designed online environment. Populytics works with all kinds of Dutch local and national governments for research projects that offer citizens a direct participation in democratic processes. I use my skills in NLP research and argument mining to support Populytics’s social and political science researchers.

I am finishing up my PhD at the Computational Linguistics and Text Mining Lab (CLTL) at the Vrije Universiteit Amsterdam (VU). My PhD is about using natural language processing (NLP) for responsible news recommender systems. I’m supervised by prof. dr. Antske Fokkens (also connected to CLTL) and prof. dr. Suzan Verberne (connected to the Text Mining group at LIACS, Leiden University).

During my PhD, I have completed a fully funded research visit through the GESIS Visiting Junior Researcher grant at the Data Science Methods group at GESIS in Cologne (March - May 2024) and have succesfully completed an internship in the Content & Creator AI Linguist team at LinkedIn in Dublin, Ireland (Summer 2023). I have also given invited talks at several international research labs and institutes, including MilaNLP Lab @ Bocconi University, FBK in Trento, and IMS @ Stuttgart University. You can download my full CV here.

I hope to continue doing interesting research with societal impact, where my interests are (but are not limited to):
-online information, argumentation, and debate;
-societally responsible AI;
-meta-science: scientific norms and methodology within and outside NLP;
-and interdisciplinarity!

Want to know more about any of my current or past projects? Ask me through email, LinkedIn, or on Bluesky . I’m always interested in new ideas or opportunities, so please contact me if you have any! 😁

News

_{23 January 2025 Our paper, “Tell Me What You Know About Sexism: Expert-LLM Interaction Strategies and Co-Created Definitions for Zero-Shot Sexism Detection” (with Indira Sen, Matteo Melis, and Gabriella Lapesa) was accepted into the Findings of NAACL 2025! This was the culmination of my research visit at the Data Science methods team at GESIS in Cologne! Preprint coming soon.}

_{6 January 2025 I have started as an NLP researcher and engineer at Populytics! Populytics is a spin-off from Delft University of Technology that provides analyses of citizens’ opinions about policy dilemmas, working with all kinds of Dutch local and national governments for research projects that offer citizens a direct participation in democratic processes. I use my skills in NLP research and opinion mining to support Populytics’s social and political science researchers.}

_{23 Sept 2024 The NWO project “Rethinking News Algorithms”, which my PhD is part of, organized a final PhD workshop to bridge the gap between academic research and practical implementation for responsible, diverse news recommendation. The final part of the afternoon was fun as well as insightful: I led an interactive “Responsible AI” role-playing game! 🕹️ Read more in my summary of the afternoon.}

_{13 Sept 2024 Had a great time at the Workshop on Computational Linguistics for Political Text Analysis (CPSS) at the KONVENS conference in Vienna, where I contributed to two papers! One paper, “A Few Hypocrites: Few-Shot Learning and Subtype Definitions for Detecting Hypocrisy Accusations in Online Climate Change Debates”, was co-authored with a group of PhD students I met at the ICA23 hackathon in Toronto! The other paper, “Topic-specific Social Science Theory in Stance Detection: a Proposal and Interdisciplinary Pilot Study on Sustainability Initiatives”, was a long-due paper from a collaboration with Ana Isabel Lopez from the communication science department. I also wrote a brief summary of both papers and my experience at the conference.}

_{15 August 2024 The first result of my GESIS research visit is published! With first author Maximilian Maurer, Julia Romberg, Negash Weldekiros, and Gabriella Lapesa we worked on a complex shared task on 𝐝𝐢𝐯𝐞𝐫𝐬𝐢𝐭𝐲 𝐚𝐧𝐝 𝐬𝐨𝐜𝐢𝐨-𝐜𝐮𝐥𝐭𝐮𝐫𝐚𝐥 𝐚𝐬𝐩𝐞𝐜𝐭𝐬 𝐢𝐧 𝐚𝐫𝐠𝐮𝐦𝐞𝐧𝐭 𝐫𝐞𝐭𝐫𝐢𝐞𝐯𝐚𝐥. Our solution placed third 🥉 in this shared task (part of the Argument Mining workshop) at ACL 2024. Read our paper or my short summary of the paper and task - it really connected well to many of my interests: diversity in recommendation and retrieval, argument mining, and socio-cultural context of NLP!}

_{–> news archive has earlier talks, events, etc.}