I checked 7 public opinion journals on Saturday, November 14, 2026 using the Crossref API. For the period November 07 to November 13, I found 4 new paper(s) in 4 journal(s).

Journal of Elections, Public Opinion and Parties

Who counts as a niche party? Programmatic distinctiveness and local party competition
Andreas Nordang Uhre, Mikael Poul Johannesson
Full text

Journal of Official Statistics

Automatically Coding Economic Activities via Semantic Search
Francesco Ortame, Mauro Bruno
Full text
Automated coding of free-text descriptions is a core challenge for National Statistical Institutes (NSIs), which must map colloquial respondent inputs to official taxonomies under strict reliability and transparency requirements. Rule-based systems, the current standard, demand extensive, ongoing human effort to author and maintain the large manual rule sets needed to cover the diversity of real world inputs. This paper evaluates embedding-based semantic retrieval as a lower-maintenance alternative, using the Italian ATECO classification as the empirical setting. We compare several knowledge base construction strategies across seven sentence transformer models (ranging from 118 million to 8 billion parameters), evaluated against 33,544 real-world queries labelled by CIRCE, Istat’s operational rule-based coder, at the 5-digit and 2-digit levels. Moderate-size models (300–700 million parameters) are competitive with much larger ones, achieving Hit@5 above 0.82 and 0.94 at the respective levels. Query length is a significant performance driver, and manual mismatch analysis reveals that roughly one in five disagreements with CIRCE reflect label noise rather than retrieval errors. Embedding-based retrieval thus offers competitive performance with no task-specific training data and a fraction of the human labour required by rule-based approaches.

Journal of Survey Statistics and Methodology

A Typology of Live Video Interviewing Paradata: Understanding, Collecting, and Leveraging Paradata to Improve Survey Data Quality
Sebastian Kocar, Andrew L Hupp, Gabriele Durrant, Tim Hanson, Matt Brown
Full text
The adoption of live video interviewing (VI) was limited until the onset of the COVID-19 pandemic. Since then, uptake has increased with methodological research focusing primarily on VI implementation and its implications for data quality, including response rates, representation, and measurement error. However, the collection and use of paradata describing the process of survey data collection within this emerging mode has so far received little attention. This study addresses this gap by developing and presenting a new typology of VI paradata aligned with the Total Survey Error (TSE) framework, which encompasses paradata from across all survey stages, including pre-data collection, recruitment, video platform, interview process, and post-interview paradata. The article presents good practices for VI paradata collection and application and is the first to systematically discuss paradata associated with the VI process. The evidence presented is based on a scoping review and critical assessment of surveys that collected VI paradata. From the scoping review, it is clear that the collection of VI paradata has thus far been limited to a relatively narrow range, has likely not been strategically planned, and the resulting paradata have generally been underused. Our comprehensive review and synthesis demonstrate that VI paradata from different survey phases have the potential to be effectively applied to assess survey data in different ways. Combined with a discussion of new examples of VI paradata, including those supported by the use of (integrated) video platforms or by artificial intelligence (AI), this study provides important evidence of how VI paradata can enhance future survey practice. The recommendation is that survey researchers should adopt a strategic, comprehensive, innovative, and empirically grounded approach to VI paradata collection and use, in order to maximize the potential of this emerging data collection mode.

Social Science Computer Review

Fine-Tuned Large Language Models for Theory-Aligned Social Science Content Analysis: Evidence From Collaborative Learning Discourse
Yoonhee Shin, Youngkwan Son, Haengkyung Lee, Minyoung Kim
Full text
Theory-based content analysis is central to social science research, but coding context-dependent interactional discourse remains difficult to scale. This study examines whether fine-tuned large language models (LLMs) can support theory-aligned, episode-level coding of complex social interaction, using socially shared metacognitive regulation (SSMR) in collaborative learning discourse as a demanding empirical case. Using a human-coded dataset of 2,372 discourse episodes from undergraduate collaborative problem-solving, we adapted the large language model content analysis (LACA) framework through an AI-aligned codebook, prompt design, and supervised fine-tuning. Prompt-only and fine-tuned models were compared across episode-level classification and multilayer SSMR coding. Fine-tuned models substantially improved agreement with human coding and predictive performance relative to prompt-only baselines. Performance was strongest for episode-level classification and several higher-support coding layers, whereas errors remained concentrated in sparse, boundary-prone, and highly interpretive categories requiring social-intent reconstruction and temporally unfolding context. The findings extend recent work on LLM-assisted qualitative and content analysis by showing both the promise and limits of supervised, theory-aligned automation for multilayer social interaction coding. Overall, the study supports a human-centered approach to LLM-assisted content analysis, in which automated coding can support more stable coding tasks while human expertise remains essential for ambiguous, boundary-prone, and interpretively demanding judgments.