Antoine Claude Lemor
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Antoine Claude Lemor has a total of 16 co-authors. Here are the top co-authors by number of shared publications:
- Éric Montpetit
Department of Political Science, Université de Montréal, Montreal, Canada
3 shared publications - Alizée Pillod
Université de Montréal, Montréal, Canada
1 shared publication Clarisse Van Belleghem
Political Science Department UCLouvain Louvain‐la‐Neuve Belgium
1 shared publication- David Aubin
Université Catholique de Louvain, Belgium
1 shared publication Frédéric Varone
Political Science Department Universite de Geneve Geneva Switzerland
1 shared publicationJean‐Louis Denis
Ecole de sante publique Universite de Montreal Montreal Quebec Canada
1 shared publication
Latest Publications
- Open Access
- 24 September 2026
- Published by Springer Nature in Scientific Data
CCF Database: A Machine-Learning-Annotated Corpus of 283,964 Canadian Climate Articles (1978–2026)
News media shape how societies perceive and respond to climate change, yet fine-grained analysis remains hindered by fragmented corpora and ad hoc coding schemes. The Canadian Climate Framing (CCF) database answers both with a large-scale bilingual annotated corpus and a generalizable annotation framework. It covers 283,964 climate-related articles from 22 Canadian news outlets (1978–2026), processed into 9,908,776 two-sentence units (83.4% English, 16.6% French). Each unit carries 65 hierarchical binary annotations spanning eight main frames, actors, events, solutions, tone, geography, and urgency, produced by 128 BERT and CamemBERT classifiers trained on 4,000+ expert-coded sentences. Against a 1,000-sentence gold standard double-coded by an independent annotator (Cohen’s κ = 0.596, Krippendorff’s α = 0.698, Gwet’s AC1 = 0.894), the classifiers reach a pooled macro F 1 of 0.866 (mean per-category macro F 1 = 0.773), and every category carries an A/B/C reliability tier. The database—sentence-level annotations, per-article aggregations, and 10,192,740 BAAI/bge-m3 embeddings in six relational tables—is openly released on Zenodo (CC-BY 4.0) as a PostgreSQL edition and an Apache Parquet mirror, refreshed roughly every six months by the CCF Observatory.
- 24 September 2026
- Published by Springer Nature in Scientific Data
Open AccessCCF Database: A Machine-Learning-Annotated Corpus of 283,964 Canadian Climate Articles (1978–2026)
News media shape how societies perceive and respond to climate change, yet fine-grained analysis remains hindered by fragmented corpora and ad hoc coding schemes. The Canadian Climate Framing (CCF) database answers both with a large-scale bilingual annotated corpus and a generalizable annotation framework. It covers 283,964 climate-related articles from 22 Canadian news outlets (1978–2026), processed into 9,908,776 two-sentence units (83.4% English, 16.6% French). Each unit carries 65 hierarchical binary annotations spanning eight main frames, actors, events, solutions, tone, geography, and urgency, produced by 128 BERT and CamemBERT classifiers trained on 4,000+ expert-coded sentences. Against a 1,000-sentence gold standard double-coded by an independent annotator (Cohen’s κ = 0.596, Krippendorff’s α = 0.698, Gwet’s AC1 = 0.894), the classifiers reach a pooled macro F 1 of 0.866 (mean per-category macro F 1 = 0.773), and every category carries an A/B/C reliability tier. The database—sentence-level annotations, per-article aggregations, and 10,192,740 BAAI/bge-m3 embeddings in six relational tables—is openly released on Zenodo (CC-BY 4.0) as a PostgreSQL edition and an Apache Parquet mirror, refreshed roughly every six months by the CCF Observatory.
- Open Access
- 13 April 2026
- Published by Center for Open Science in SocArXiv
LLM Tool: A Hybrid Pipeline for Automated High-Throughput Text Annotation Using Local Language Models and BERT Classifiers
Large language models now routinely annotate text in computational social science, but they do not hold up at corpus sizes of several million sentences. Proprietary LLMs are financially prohibitive, local open-weight LLMs take days or weeks of computation, and both remain opaque and hard to reproduce. Using LLMs to train dedicated classifiers solves these problems, yet the approach itself remains sparsely tested in the social sciences and largely inaccessible to researchers without engineering support. We present LLMTool, an open-source Python package that runs the full hybrid workflow from a command line. On a bilingual corpus of 38,451 Canadian parliamentary debates and news media texts coded across four dimensions, classifiers trained on the best LLM labels reach amean Micro F1 of 68.9%. Open-weight models such as GPT-OSS match one of the best proprietary models available, GPT-5, and deliver a 109–395× inference speedup over directLLM annotation on standard workstations
- 13 April 2026
- Published by Center for Open Science in SocArXiv
Open AccessLLM Tool: A Hybrid Pipeline for Automated High-Throughput Text Annotation Using Local Language Models and BERT Classifiers
Large language models now routinely annotate text in computational social science, but they do not hold up at corpus sizes of several million sentences. Proprietary LLMs are financially prohibitive, local open-weight LLMs take days or weeks of computation, and both remain opaque and hard to reproduce. Using LLMs to train dedicated classifiers solves these problems, yet the approach itself remains sparsely tested in the social sciences and largely inaccessible to researchers without engineering support. We present LLMTool, an open-source Python package that runs the full hybrid workflow from a command line. On a bilingual corpus of 38,451 Canadian parliamentary debates and news media texts coded across four dimensions, classifiers trained on the best LLM labels reach amean Micro F1 of 68.9%. Open-weight models such as GPT-OSS match one of the best proprietary models available, GPT-5, and deliver a 109–395× inference speedup over directLLM annotation on standard workstations
- Open Access
- 8 April 2026
- Published by Center for Open Science in SocArXiv
The Death of Policy Process Theories? Agenda-Setting in the Age of Machines
The Multiple Streams Framework, Punctuated Equilibrium Theory, the Advocacy Coalition Framework, and the Narrative Policy Framework rest on five tacit premises about political information so self-evident when the theories were formulated that they were never explicitly stated: that political information is human-produced, filtered by identifiable gatekeepers, reflective of authentic public opinion, distinguishable from noise, and anchored in verifiable events. However, a radical transformation of the informational ecosystem completely upends these premises: machines — AI and LLMs — now produce political information indistinguishable from that produced by humans. As a consequence, this article argues that the canonical theories are, in the Kuhnian sense, dying. Through agenda-setting, where the four theories converge, it shows that their core mechanisms lose the substrate on which they were built to operate. It proposes a new Epistemic Policy Process (EPP) theory based on three dimensions to circumscribe the conditions under which the classical theories can still hold, and maybe stay alive.
- 8 April 2026
- Published by Center for Open Science in SocArXiv
Open AccessThe Death of Policy Process Theories? Agenda-Setting in the Age of Machines
The Multiple Streams Framework, Punctuated Equilibrium Theory, the Advocacy Coalition Framework, and the Narrative Policy Framework rest on five tacit premises about political information so self-evident when the theories were formulated that they were never explicitly stated: that political information is human-produced, filtered by identifiable gatekeepers, reflective of authentic public opinion, distinguishable from noise, and anchored in verifiable events. However, a radical transformation of the informational ecosystem completely upends these premises: machines — AI and LLMs — now produce political information indistinguishable from that produced by humans. As a consequence, this article argues that the canonical theories are, in the Kuhnian sense, dying. Through agenda-setting, where the four theories converge, it shows that their core mechanisms lose the substrate on which they were built to operate. It proposes a new Epistemic Policy Process (EPP) theory based on three dimensions to circumscribe the conditions under which the classical theories can still hold, and maybe stay alive.
- Open Access
- 7 April 2026
- Published by Center for Open Science in SocArXiv
YouPol: A Collaborative Research Infrastructure and Database for Political Content on YouTube and TikTok
This paper presents YouPol (YouTube and TikTok Political Observatory and Longitudinal database), a permanently updated research infrastructure that captures what political content creators actually say on video platforms. As of April 2026 and continuously expanding, the corpus comprises 25,397 videos from 68 channels across France and Quebec, with full speaker-diarized transcripts (645,738 segments, 3.18 million annotated sentences) and 7.7 million archived comments. The infrastructure includes an independent transcription pipeline that produces high-quality transcripts regardless of platform-provided captions, and an LLM-in-the-loop annotation framework built on the open-source LLM Tool platform (Lemor et al., 2025) that can train sentence-level classifiers for any research project, with current projects covering political content detection, far-right ideology, gendered rhetoric, and neo-reactionary discourse. To produce transcription and metadata updates in real time, YouPol also introduces the YouPol Collaborative Computing Network (YCCN), which allows any collaborating researcher to contribute processing capacity from their own machine, freeing the observatory from dependence on institutional computing clusters. YouPol addresses four gaps in the literature: (1) the ideological substance of political video content remains empirically inaccessible through metadata alone; (2) content deletion and deplatforming erase material before researchers can study it; (3) longitudinal engagement dynamics are underexploited; and (4) no existing dataset preserves comments over time or tracks their deletion. The observatory has already preserved 2,305 videos and three entirely deleted channels that are no longer available on the platform. The dataset and API are available at https://data.you-pol.com/.
- 7 April 2026
- Published by Center for Open Science in SocArXiv
Open AccessYouPol: A Collaborative Research Infrastructure and Database for Political Content on YouTube and TikTok
This paper presents YouPol (YouTube and TikTok Political Observatory and Longitudinal database), a permanently updated research infrastructure that captures what political content creators actually say on video platforms. As of April 2026 and continuously expanding, the corpus comprises 25,397 videos from 68 channels across France and Quebec, with full speaker-diarized transcripts (645,738 segments, 3.18 million annotated sentences) and 7.7 million archived comments. The infrastructure includes an independent transcription pipeline that produces high-quality transcripts regardless of platform-provided captions, and an LLM-in-the-loop annotation framework built on the open-source LLM Tool platform (Lemor et al., 2025) that can train sentence-level classifiers for any research project, with current projects covering political content detection, far-right ideology, gendered rhetoric, and neo-reactionary discourse. To produce transcription and metadata updates in real time, YouPol also introduces the YouPol Collaborative Computing Network (YCCN), which allows any collaborating researcher to contribute processing capacity from their own machine, freeing the observatory from dependence on institutional computing clusters. YouPol addresses four gaps in the literature: (1) the ideological substance of political video content remains empirically inaccessible through metadata alone; (2) content deletion and deplatforming erase material before researchers can study it; (3) longitudinal engagement dynamics are underexploited; and (4) no existing dataset preserves comments over time or tracks their deletion. The observatory has already preserved 2,305 videos and three entirely deleted channels that are no longer available on the platform. The dataset and API are available at https://data.you-pol.com/.
- Open Access
- 6 January 2025
- Published by Bristol University Press in Policy & Politics
- Vol. -1 (aop) , 1-20
Why did the influence of experts erode during the COVID-19 pandemic?
In the face of protracted crises like climate change or pandemics, the influence of expert scientific projections on public policy is crucial yet evolves over time. This study offers an empirical demonstration of a previously fragmented theory: the diminishing influence of scientific projections on policy over time. Using a comprehensive mixed-method analysis, the article studies the relationship between expert projections, policy stringency and public support in Quebec during the COVID-19 pandemic. Scientific projections that put forward worst-case scenarios have a considerable impact on policies made in the early stages of a crisis. However, as these catastrophic projections instil a sense of fatalism as the crisis lasts, they inadvertently lead to diminished public support for both the policies and the scientific projections themselves. The implications of these findings for scientists and experts are discussed, highlighting the importance of adapting projections and knowledge communication strategies as the crisis unfolds.
- 6 January 2025
- Published by Bristol University Press in Policy & Politics
- Vol. -1 (aop) , 1-20
Open AccessWhy did the influence of experts erode during the COVID-19 pandemic?
In the face of protracted crises like climate change or pandemics, the influence of expert scientific projections on public policy is crucial yet evolves over time. This study offers an empirical demonstration of a previously fragmented theory: the diminishing influence of scientific projections on policy over time. Using a comprehensive mixed-method analysis, the article studies the relationship between expert projections, policy stringency and public support in Quebec during the COVID-19 pandemic. Scientific projections that put forward worst-case scenarios have a considerable impact on policies made in the early stages of a crisis. However, as these catastrophic projections instil a sense of fatalism as the crisis lasts, they inadvertently lead to diminished public support for both the policies and the scientific projections themselves. The implications of these findings for scientists and experts are discussed, highlighting the importance of adapting projections and knowledge communication strategies as the crisis unfolds.
- Open Access
- 20 July 2024
- Published by Wiley in Governance
- Vol. 38 (2)
Network dynamics in public health advisory systems: A comparative analysis of scientific advice for COVID‐19 in Belgium, Quebec, Sweden, and Switzerland
This study presents a dual‐method approach to systematically analyze public health advisory networks during the COVID‐19 pandemic across four jurisdictions: Belgium, Quebec, Sweden, and Switzerland. Using network analysis inspired by egocentric analysis and a subsystems approach adapted to public health, the research investigates network structures and their openness to new actors and ideas. The findings reveal significant variations in network configurations, with differences in density, centralization, and the role of central actors. The study also uncovers a relation between network openness and its structural attributes, highlighting the impact of network composition on the flow and control of expert advice. These insights into public health advisory networks contribute to understanding the interface between scientific advice and policymaking, emphasizing the importance of network characteristics in shaping the influence of expert advisors. The article underscores the relevance of systematic network descriptions in public policy, offering reflections on expert accountability, information diversity, and the broader implications for democratic governance.
- 20 July 2024
- Published by Wiley in Governance
- Vol. 38 (2)
Open AccessNetwork dynamics in public health advisory systems: A comparative analysis of scientific advice for COVID‐19 in Belgium, Quebec, Sweden, and Switzerland
This study presents a dual‐method approach to systematically analyze public health advisory networks during the COVID‐19 pandemic across four jurisdictions: Belgium, Quebec, Sweden, and Switzerland. Using network analysis inspired by egocentric analysis and a subsystems approach adapted to public health, the research investigates network structures and their openness to new actors and ideas. The findings reveal significant variations in network configurations, with differences in density, centralization, and the role of central actors. The study also uncovers a relation between network openness and its structural attributes, highlighting the impact of network composition on the flow and control of expert advice. These insights into public health advisory networks contribute to understanding the interface between scientific advice and policymaking, emphasizing the importance of network characteristics in shaping the influence of expert advisors. The article underscores the relevance of systematic network descriptions in public policy, offering reflections on expert accountability, information diversity, and the broader implications for democratic governance.
- Open Access
- 22 March 2024
- Published by Oxford University Press (OUP) in Policy and Society
- Vol. 43 (3) , 289-303
Exploring the role of uncertainty, emotions, and scientific discourse during the COVID-19 pandemic
This article examines the interplay between uncertainty, emotions, and scientific discourse in shaping COVID-19 policies in Quebec, Canada. Through the application of natural language processing (NLP) techniques, indices were developped to measure sentiments of uncertainty among policymakers, their negative sentiments, and the prevalence of scientific statements. The study reveals that while sentiments of uncertainty led to the adoption of stringent policies, scientific statements and the evidence they conveyed were associated with a relaxation of such policies, as they offered reassurance and mitigated negative sentiments. Furthermore, the findings suggest that scientific statements encouraged stricter policies only in contexts of high uncertainty. This research contributes to the theoretical understanding of the interplay between emotional and cognitive dynamics in health crisis policymaking. It emphasizes the need for a nuanced understanding of how science may be used in the face of uncertainty, especially when democratic processes are set aside. Methodologically, it demonstrates the potential of NLP in policy analysis.
- 22 March 2024
- Published by Oxford University Press (OUP) in Policy and Society
- Vol. 43 (3) , 289-303
Open AccessExploring the role of uncertainty, emotions, and scientific discourse during the COVID-19 pandemic
This article examines the interplay between uncertainty, emotions, and scientific discourse in shaping COVID-19 policies in Quebec, Canada. Through the application of natural language processing (NLP) techniques, indices were developped to measure sentiments of uncertainty among policymakers, their negative sentiments, and the prevalence of scientific statements. The study reveals that while sentiments of uncertainty led to the adoption of stringent policies, scientific statements and the evidence they conveyed were associated with a relaxation of such policies, as they offered reassurance and mitigated negative sentiments. Furthermore, the findings suggest that scientific statements encouraged stricter policies only in contexts of high uncertainty. This research contributes to the theoretical understanding of the interplay between emotional and cognitive dynamics in health crisis policymaking. It emphasizes the need for a nuanced understanding of how science may be used in the face of uncertainty, especially when democratic processes are set aside. Methodologically, it demonstrates the potential of NLP in policy analysis.