computational social science
PulseAugur coverage of computational social science — every cluster mentioning computational social science across labs, papers, and developer communities, ranked by signal.
-
New framework analyzes online ideology beyond left-right spectrum
A new conceptual framework aims to move beyond the traditional left-right political spectrum when analyzing online discourse. This framework, proposed by Kenneth Joseph Koehler, views ideology as a multi-level socio-cog…
-
LLM pipeline extracts political claims from social media at scale
Researchers have developed a pipeline utilizing large language models (LLMs) to extract and categorize claims from extensive social media datasets. This method was applied to Twitter data concerning the 2020 US presiden…
-
New method calibrates AI bias tests by addressing embedding space anisotropy
Researchers have proposed using Zero-phase Component Analysis (ZCA) whitening as a pre-processing step for the Word Embedding Association Test (WEAT). This method aims to address concerns about the reliability of WEAT, …
-
New Protocol Validates LLM Embeddings for Social Science Research
A new research paper introduces the Construct Validity Protocol (CVP) to address the "Proxy Presumption" in computational social science, where geometric properties of embeddings are used as direct measures of social co…
-
New framework evaluates interdisciplinary discourse in scholarly publications
Researchers have developed a new framework to evaluate how scholarly publications engage with ideas from different disciplines. This framework is specifically designed for interdisciplinary work, particularly in Natural…
-
LLM Annotators Show Social-Desirability Bias in Social Science Research
A new paper investigates social-desirability bias in LLM annotators used for computational social science. Researchers found that three open-source models (Zephyr, Mistral-Instruct, and Qwen2.5-Instruct) exhibit differe…
-
LLM text analysis framework uses covariates for subgroup hypothesis generation
Researchers have developed a new framework for conditional hypothesis generation in LLM-based text analysis. This method incorporates researcher-specified covariates to ensure that discovered language patterns reflect g…