Adam Visokay
Author directory2026
Social Construction of Urban Space: Using LLMs to Identify Neighborhood Boundaries From Craigslist Ads
Adam Visokay | Ruth Bagley | Chris Hess | Ian Kennedy | Kyle Crowder | Rob Voigt | Denis Peskoff
Proceedings of the Seventh Workshop on Natural Language Processing and Computational Social Science
Adam Visokay | Ruth Bagley | Chris Hess | Ian Kennedy | Kyle Crowder | Rob Voigt | Denis Peskoff
Proceedings of the Seventh Workshop on Natural Language Processing and Computational Social Science
Rental listings offer a window into how urban space is socially constructed through language. We analyze Chicago Craigslist rental advertisements from 2018 to 2024 to examine how listing agents characterize neighborhoods, identifying mismatches between institutional boundaries and neighborhood claims. Through manual and large language model annotation, we classify unstructured listings from Craigslist according to their neighborhood. Further geospatial analysis reveals three distinct patterns: properties with conflicting neighborhood designations due to competing spatial definitions, border properties with valid claims to adjacent neighborhoods, and “reputation laundering" where listings claim association with distant, desirable neighborhoods. Through topic modeling, we identify patterns that correlate with spatial positioning: listings further from neighborhood centers emphasize different amenities than centrally-located units. Natural language processing techniques reveal how definitions of urban spaces are contested in ways that traditional methods overlook.
Multi-Perspective LLM Annotations for Valid Analyses in Subjective Tasks
Navya Mehrotra | Adam Visokay | Kristina Gligorić
Proceedings of the 15th International Joint Conference on Natural Language Processing and the 5th Conference of the Asia-Pacific Chapter of the Association for Computational Linguistics (Volume 1: Long Papers)
Navya Mehrotra | Adam Visokay | Kristina Gligorić
Proceedings of the 15th International Joint Conference on Natural Language Processing and the 5th Conference of the Asia-Pacific Chapter of the Association for Computational Linguistics (Volume 1: Long Papers)
Large language models are increasingly used to annotate texts, but their outputs reflect some human perspectives better than others. Existing methods for correcting LLM annotation error assume a single ground truth. However, this assumption fails in subjective tasks where disagreement across demographic groups is meaningful. Here we introduce Perspective-Driven Inference, a method that treats the distribution of annotations across groups as the quantity of interest, and estimates it using a small human annotation budget. We contribute an adaptive sampling strategy that concentrates human annotation effort on groups where LLM proxies are least accurate. We evaluate on politeness and offensiveness rating tasks, showing targeted improvements for harder-to-model demographic groups relative to uniform sampling baselines, while maintaining coverage.
2023
GPT Deciphering Fedspeak: Quantifying Dissent Among Hawks and Doves
Denis Peskoff | Adam Visokay | Sander Schulhoff | Benjamin Wachspress | Alan Blinder | Brandon Stewart
Findings of the Association for Computational Linguistics: EMNLP 2023
Denis Peskoff | Adam Visokay | Sander Schulhoff | Benjamin Wachspress | Alan Blinder | Brandon Stewart
Findings of the Association for Computational Linguistics: EMNLP 2023
Markets and policymakers around the world hang on the consequential monetary policy decisions made by the Federal Open Market Committee (FOMC). Publicly available textual documentation of their meetings provides insight into members’ attitudes about the economy. We use GPT-4 to quantify dissent among members on the topic of inflation. We find that transcripts and minutes reflect the diversity of member views about the macroeconomic outlook in a way that is lost or omitted from the public statements. In fact, diverging opinions that shed light upon the committee’s “true” attitudes are almost entirely omitted from the final statements. Hence, we argue that forecasting FOMC sentiment based solely on statements will not sufficiently reflect dissent among the hawks and doves.