Key papers in General Social Sciences
Pofolia’s corpus holds 66 papers from the General Social Sciences subfield (2012–2024). The list below starts with the most cited.
Most cited
Ranked by citation count. Because citations accumulate over time, this list naturally leans towards work published a few years ago; for where the field is now, see “recently added”.
Text as Data: The Promise and Pitfalls of Automatic Content Analysis Methods for Political Texts
Political Analysis · 2013 · Q1 · SJR 4.00 · FWCI 1244.63 · 3,200 citations · Open access
Automated text analysis methods offer a powerful way to reduce the cost of analyzing large political text collections, fulfilling a long-standing promise in political science.
Structural Topic Models for Open‐Ended Survey Responses
American Journal of Political Science · 2014 · Q1 · SJR 6.00 · FWCI 550.55 · 1,949 citations
This paper introduces the Structural Topic Model (STM), a semi-automated machine learning approach for analyzing open-ended survey responses, offering an alternative to traditional human coding.
<b>stm</b>: An <i>R</i> Package for Structural Topic Models
Journal of Statistical Software · 2019 · Q1 · SJR 3.00 · FWCI 981.10 · 1,525 citations · Open access
The 'stm' R package is introduced, enabling researchers to estimate structural topic models that incorporate document-level metadata using a fast variational approximation.
Theories of the Information Society
2014 · FWCI 161.38 · 1,287 citations
This book critically examines the concept of the 'Information Society,' arguing against its widespread adoption and instead advocating for an analysis of the 'informatization' of existing social structures.
Word embeddings quantify 100 years of gender and ethnic stereotypes
Proceedings of the National Academy of Sciences · 2018 · Q1 · SJR 3.00 · FWCI 1161.85 · 1,103 citations
Researchers developed a method using word embeddings trained on 100 years of US text data to quantify evolving gender and ethnic stereotypes.
Ten Steps in Scale Development and Reporting: A Guide for Researchers
Communication Methods and Measures · 2017 · Q1 · SJR 2.00 · FWCI 339.20 · 1,088 citations
This guide outlines 10 essential steps for researchers to improve the rigor and clarity of scale development and reporting, addressing common inconsistencies with best practices.
A Topic Modeling Comparison Between LDA, NMF, Top2Vec, and BERTopic to Demystify Twitter Posts
Frontiers in Sociology · 2022 · Q1 · FWCI 649.31 · 905 citations · Open access
This study evaluates four topic modeling techniques (LDA, NMF, Top2Vec, BERTopic) for analyzing Twitter data, finding BERTopic and NMF most effective.
La guerra contra las mujeres
2016 · FWCI 475.52 · 868 citations
This work argues that escalating violence against women, exemplified by systematic murders in Ciudad Juárez, is a global phenomenon linked to neoliberalism, authoritarianism, and unresolved modernity-coloniality.
Applying LDA Topic Modeling in Communication Research: Toward a Valid and Reliable Methodology
Communication Methods and Measures · 2018 · Q1 · SJR 2.00 · FWCI 489.70 · 818 citations
This paper proposes a standardized methodology to address key challenges in applying Latent Dirichlet Allocation (LDA) topic modeling for communication research, aiming to improve its validity and reliability.
Generational differences in the workplace: A review of the evidence and directions for future research
Journal of Organizational Behavior · 2013 · Q1 · SJR 3.00 · FWCI 372.73 · 786 citations
Research on generational differences in the workplace is largely descriptive and lacks theoretical depth, with inconsistent evidence making generalizations difficult.
A Model of Text for Experimentation in the Social Sciences
Journal of the American Statistical Association · 2016 · Q1 · SJR 3.00 · FWCI 479.56 · 733 citations
This paper introduces a hierarchical mixed membership model for text analysis that allows researchers to experimentally assess the drivers of topical content in documents.
Trending: The Promises and the Challenges of Big Social Data
University of Minnesota Press eBooks · 2012 · FWCI 527.03 · 683 citations
Big social data, defined by its massive size (dozens of terabytes to petabytes), presents both opportunities and challenges for the humanities and social sciences.
Computational Grounded Theory: A Methodological Framework
Sociological Methods & Research · 2017 · Q1 · SJR 3.00 · FWCI 215.57 · 663 citations
A new three-step framework, Computational Grounded Theory (CGT), integrates human interpretation with computational pattern detection for more rigorous content analysis of qualitative text data.
La sociedad del cansancio
Herder eBooks · 2017 · FWCI 848.31 · 656 citations
This philosophical text proposes that contemporary society has shifted from a disciplinary model to a 'burnout society' characterized by excessive positivity and self-exploitation.
Topic Modeling in Management Research: Rendering New Theory from Textual Data
Academy of Management Annals · 2019 · Q1 · SJR 14.00 · FWCI 422.22 · 596 citations
Topic modeling, a computational method from computer science, is increasingly used by management researchers to uncover new theories and conceptual relationships from textual data.
Beyond prediction: Using big data for policy problems
Science · 2017 · Q1 · SJR 10.00 · FWCI 589.64 · 580 citations
Machine learning excels at prediction, but bridging the gap to actual policy decisions requires understanding underlying assumptions for optimized data-driven outcomes.
Quantitative analysis of large amounts of journalistic texts using topic modelling
Digital Journalism · 2015 · Q1 · SJR 3.00 · FWCI 201.78 · 529 citations
Latent Dirichlet Allocation (LDA) topic modelling is proposed as a method to automatically organize and analyze vast archives of news content by identifying latent topics based on word patterns.
AN ENQUIRY CONCERNING HUMAN UNDERSTANDING
Cambridge University Press eBooks · 2012 · FWCI 178.09 · 494 citations
David Hume's 1748 philosophical work argues that human knowledge is limited and heavily relies on non-rational mental habits, not pure reason.
Simultaneously Discovering and Quantifying Risk Types from Textual Risk Disclosures
Management Science · 2014 · Q1 · SJR 6.00 · FWCI 252.70 · 489 citations
A new topic modeling approach, a variation of Latent Dirichlet Allocation, can simultaneously discover and quantify risk types from corporate textual disclosures, outperforming existing methods.
Computer-Assisted Text Analysis for Comparative Politics
Political Analysis · 2015 · Q1 · SJR 4.00 · FWCI 402.69 · 488 citations · Open access
This article introduces practical methods for analyzing textual data in comparative politics, focusing on cross-language challenges and demonstrating the Structural Topic Model (STM) with translated data.
Recently added
Can Generative AI improve social science?
Proceedings of the National Academy of Sciences · 2024 · Q1 · SJR 3.00 · FWCI 368.77 · 244 citations · Open access
Generative AI can enhance social science research methods like surveys, online experiments, and content analysis, but its biases and ethical challenges require open-source infrastructure to ensure quality and access.
Evolution of artificial intelligence research in Technological Forecasting and Social Change: Research topics, trends, and future directions
Technological Forecasting and Social Change · 2023 · Q1 · SJR 3.00 · FWCI 338.13 · 312 citations
AI research in Technological Forecasting and Social Change (TF&SC) reveals eight key topics, with healthcare, circular economy, consumer adoption, and decision-making showing rising trends.
A Topic Modeling Comparison Between LDA, NMF, Top2Vec, and BERTopic to Demystify Twitter Posts
Frontiers in Sociology · 2022 · Q1 · FWCI 649.31 · 905 citations · Open access
This study evaluates four topic modeling techniques (LDA, NMF, Top2Vec, BERTopic) for analyzing Twitter data, finding BERTopic and NMF most effective.
academictwitteR: an R package to access the Twitter Academic Research Product Track v2 API endpoint
The Journal of Open Source Software · 2021 · FWCI 252.63 · 230 citations · Open access
academictwitteR is a new R package that simplifies access to the Twitter Academic Research Product Track v2 API endpoint.
Word Embeddings: What Works, What Doesn’t, and How to Tell the Difference for Applied Research
The Journal of Politics · 2021 · Q1 · SJR 3.00 · FWCI 194.31 · 245 citations
Political science research using word embeddings shows results are generally robust to parameter choices (context window, dimensions, pretrained vs. local fit) across corpora and languages.
Add this field to your daily feed
Pick your interests and new work in your area arrives every day, summarised. Full summaries live in the app.
Open the app