Maxwell A. Weinzierl
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Maxwell A. Weinzierl has a total of 6 co-authors. Here are the top co-authors by number of shared publications:
- Sanda Maria Harabagiu
Human Language Technology Research Institute, Department of Computer Science, The University of Texas at Dallas, Richardson, TX, USA
5 shared publications Sanda Harabagiu
Human Language Technology Research Institute The University of Texas at Dallas
3 shared publications- Suellen Hopfer
Department of Health, Society & Behavior, UC Irvine Joe C. Wen School of Population & Public Health, University of California, Irvine, CA 92697, USA
2 shared publications Ramon Maldonado
Human Language Technology Research Institute, Department of Computer Science, Erik Jonsson School of Engineering & Computer Science, University of Texas at Dallas, Richardson, Texas, USA
1 shared publicationSanda M Harabagiu
Human Language Technology Research Institute, Department of Computer Science, Erik Jonsson School of Engineering & Computer Science, University of Texas at Dallas, Richardson, Texas, USA
1 shared publicationSanda M. Harabagiu
Human Language Technology Research Institute The University of Texas at Dallas
1 shared publication
Latest Publications
- Open Access
- 1 January 2025
- Published by Association for Computational Linguistics (ACL)
- p. 6795-6814
Investigating Controversy Framing across Topics on Social Media
Maxwell Weinzierl, Sanda M. Harabagiu. Findings of the Association for Computational Linguistics: EMNLP 2025. 2025.
- 1 January 2025
- Published by Association for Computational Linguistics (ACL)
- p. 6795-6814
Open AccessInvestigating Controversy Framing across Topics on Social Media
Maxwell Weinzierl, Sanda M. Harabagiu. Findings of the Association for Computational Linguistics: EMNLP 2025. 2025.
- Open Access
- 1 January 2024
- Published by Association for Computational Linguistics (ACL)
- p. 1617-1631
Discovering and Articulating Frames of Communication from Social Media Using Chain-of-Thought Reasoning
Maxwell Weinzierl, Sanda Harabagiu. Proceedings of the 18th Conference of the European Chapter of the Association for Computational Linguistics (Volume 1: Long Papers). 2024.
- 1 January 2024
- Published by Association for Computational Linguistics (ACL)
- p. 1617-1631
Open AccessDiscovering and Articulating Frames of Communication from Social Media Using Chain-of-Thought Reasoning
Maxwell Weinzierl, Sanda Harabagiu. Proceedings of the 18th Conference of the European Chapter of the Association for Computational Linguistics (Volume 1: Long Papers). 2024.
- Open Access
- 1 January 2024
- Published by Association for Computational Linguistics (ACL)
- p. 861-880
Tree-of-Counterfactual Prompting for Zero-Shot Stance Detection
Maxwell Weinzierl, Sanda Harabagiu. Proceedings of the 62nd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers). 2024.
- 1 January 2024
- Published by Association for Computational Linguistics (ACL)
- p. 861-880
Open AccessTree-of-Counterfactual Prompting for Zero-Shot Stance Detection
Maxwell Weinzierl, Sanda Harabagiu. Proceedings of the 62nd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers). 2024.
- Top Cited PapersOpen Access
- 1 January 2023
- Published by Association for Computational Linguistics (ACL)
- p. 12597-12609
Identification of Multimodal Stance Towards Frames of Communication
Maxwell Weinzierl, Sanda Harabagiu. Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing. 2023.
- 1 January 2023
- Published by Association for Computational Linguistics (ACL)
- p. 12597-12609
Top Cited PapersOpen AccessIdentification of Multimodal Stance Towards Frames of Communication
Maxwell Weinzierl, Sanda Harabagiu. Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing. 2023.
- Open Access
- 17 November 2022
- Published by Oxford University Press (OUP) in Journal of the American Medical Informatics Association
- Vol. 30 (2) , 329-339
Epidemic Question Answering: question generation and entailment for Answer Nugget discovery
The rapidly growing body of communications during the COVID-19 pandemic posed a challenge to information seekers, who struggled to find answers to their specific and changing information needs. We designed a Question Answering (QA) system capable of answering ad-hoc questions about the COVID-19 disease, its causal virus SARS-CoV-2, and the recommended response to the pandemic. The QA system incorporates, in addition to relevance models, automatic generation of questions from relevant sentences. We relied on entailment between questions for (1) pinpointing answers and (2) selecting novel answers early in the list of its results. The QA system produced state-of-the-art results when processing questions asked by experts (eg, researchers, scientists, or clinicians) and competitive results when processing questions asked by consumers of health information. Although state-of-the-art models for question generation and question entailment were used, more than half of the answers were missed, due to the limitations of the relevance models employed. Although question entailment enabled by automatic question generation is the cornerstone of our QA system’s architecture, question entailment did not prove to always be reliable or sufficient in ranking the answers. Question entailment should be enhanced with additional inferential capabilities. The QA system presented in this article produced state-of-the-art results processing expert questions and competitive results processing consumer questions. Improvements should be considered by using better relevance models and enhanced inference methods. Moreover, experts and consumers have different answer expectations, which should be accounted for in future QA development.
- 17 November 2022
- Published by Oxford University Press (OUP) in Journal of the American Medical Informatics Association
- Vol. 30 (2) , 329-339
Open AccessEpidemic Question Answering: question generation and entailment for Answer Nugget discovery
The rapidly growing body of communications during the COVID-19 pandemic posed a challenge to information seekers, who struggled to find answers to their specific and changing information needs. We designed a Question Answering (QA) system capable of answering ad-hoc questions about the COVID-19 disease, its causal virus SARS-CoV-2, and the recommended response to the pandemic. The QA system incorporates, in addition to relevance models, automatic generation of questions from relevant sentences. We relied on entailment between questions for (1) pinpointing answers and (2) selecting novel answers early in the list of its results. The QA system produced state-of-the-art results when processing questions asked by experts (eg, researchers, scientists, or clinicians) and competitive results when processing questions asked by consumers of health information. Although state-of-the-art models for question generation and question entailment were used, more than half of the answers were missed, due to the limitations of the relevance models employed. Although question entailment enabled by automatic question generation is the cornerstone of our QA system’s architecture, question entailment did not prove to always be reliable or sufficient in ranking the answers. Question entailment should be enhanced with additional inferential capabilities. The QA system presented in this article produced state-of-the-art results processing expert questions and competitive results processing consumer questions. Improvements should be considered by using better relevance models and enhanced inference methods. Moreover, experts and consumers have different answer expectations, which should be accounted for in future QA development.
- 30 May 2022
- Published by Springer Nature in Journal of Behavioral Medicine
- Vol. 46 (1-2) , 253-275
Scaling up the discovery of hesitancy profiles by identifying the framing of beliefs towards vaccine confidence in Twitter discourse
Our study focused on the discovery of how vaccine hesitancy is framed in Twitter discourse, allowing us to recognize at-scale all tweets that evoke any of the hesitancy framings as well as the stance of the tweet authors towards the frame. By categorizing the hesitancy framings that propagate misinformation, address issues of trust in vaccines, or highlight moral issues or civil rights, we were able to empirically recognize their ontological commitments. Ontological commitments of vaccine hesitancy framings couples with the stance of tweet authors allowed us to identify hesitancy profiles for two most controversial yet effective and underutilized vaccines for which there remains substantial reluctance among the public: the Human Papillomavirus and the COVID-19 vaccines. The discovered hesitancy profiles inform public health messaging approaches to effectively reach Twitter users with promise to shift or bolster vaccine attitudes.
- 30 May 2022
- Published by Springer Nature in Journal of Behavioral Medicine
- Vol. 46 (1-2) , 253-275
Scaling up the discovery of hesitancy profiles by identifying the framing of beliefs towards vaccine confidence in Twitter discourse
Our study focused on the discovery of how vaccine hesitancy is framed in Twitter discourse, allowing us to recognize at-scale all tweets that evoke any of the hesitancy framings as well as the stance of the tweet authors towards the frame. By categorizing the hesitancy framings that propagate misinformation, address issues of trust in vaccines, or highlight moral issues or civil rights, we were able to empirically recognize their ontological commitments. Ontological commitments of vaccine hesitancy framings couples with the stance of tweet authors allowed us to identify hesitancy profiles for two most controversial yet effective and underutilized vaccines for which there remains substantial reluctance among the public: the Human Papillomavirus and the COVID-19 vaccines. The discovered hesitancy profiles inform public health messaging approaches to effectively reach Twitter users with promise to shift or bolster vaccine attitudes.
- 18 November 2021
- Published by Elsevier in Journal of Biomedical Informatics
- Vol. 124, 103955
Automatic detection of COVID-19 vaccine misinformation with graph link prediction
- 18 November 2021
- Published by Elsevier in Journal of Biomedical Informatics
- Vol. 124, 103955
Automatic detection of COVID-19 vaccine misinformation with graph link prediction
- Open Access
Automatic Detection of COVID-19 Vaccine Misinformation with Graph Link Prediction
Enormous hope in the efficacy of vaccines became recently a successful reality in the fight against the COVID-19 pandemic. However, vaccine hesitancy, fueled by exposure to social media misinformation about COVID-19 vaccines became a major hurdle. Therefore, it is essential to automatically detect where misinformation about COVID-19 vaccines on social media is spread and what kind of misinformation is discussed, such that inoculation interventions can be delivered at the right time and in the right place, in addition to interventions designed to address vaccine hesitancy. This paper is addressing the first step in tackling hesitancy against COVID-19 vaccines, namely the automatic detection of known misinformation about the vaccines on Twitter, the social media platform that has the highest volume of conversations about COVID-19 and its vaccines. We present CoVaxLies, a new dataset of tweets judged relevant to several misinformation targets about COVID-19 vaccines on which a novel method of detecting misinformation was developed. Our method organizes CoVaxLies in a Misinformation Knowledge Graph as it casts misinformation detection as a graph link prediction problem. The misinformation detection method detailed in this paper takes advantage of the link scoring functions provided by several knowledge embedding methods. The experimental results demonstrate the superiority of this method when compared with classification-based methods, widely used currently.
Open AccessAutomatic Detection of COVID-19 Vaccine Misinformation with Graph Link Prediction
Enormous hope in the efficacy of vaccines became recently a successful reality in the fight against the COVID-19 pandemic. However, vaccine hesitancy, fueled by exposure to social media misinformation about COVID-19 vaccines became a major hurdle. Therefore, it is essential to automatically detect where misinformation about COVID-19 vaccines on social media is spread and what kind of misinformation is discussed, such that inoculation interventions can be delivered at the right time and in the right place, in addition to interventions designed to address vaccine hesitancy. This paper is addressing the first step in tackling hesitancy against COVID-19 vaccines, namely the automatic detection of known misinformation about the vaccines on Twitter, the social media platform that has the highest volume of conversations about COVID-19 and its vaccines. We present CoVaxLies, a new dataset of tweets judged relevant to several misinformation targets about COVID-19 vaccines on which a novel method of detecting misinformation was developed. Our method organizes CoVaxLies in a Misinformation Knowledge Graph as it casts misinformation detection as a graph link prediction problem. The misinformation detection method detailed in this paper takes advantage of the link scoring functions provided by several knowledge embedding methods. The experimental results demonstrate the superiority of this method when compared with classification-based methods, widely used currently.
- Open Access
Scaling Up the Discovery of Hesitancy Profiles by Identifying the Framing of Beliefs towards Vaccine Confidence in Twitter Discourse
Our study focused on the inference of the framing of confidence in the HPV vaccine throughout a collection of 422,078 tweets as well as the framing of confidence in the COVID-19 vaccines through a collection of 5,865,046 tweets. The vaccine confidence framings were inferred by using a novel Question/Answering framework enabling the derivation of a misinformation taxonomy as well as trust taxonomies for these two vaccines. These taxonomies, along with the analysis of vaccine literacy, the implied moral foundations and the tension between vaccine mandates and civil rights allowed us to discover several profiles of hesitancy for each vaccine across 138,779 Twitter users referring to confidence in HPV vaccine and 665,798 users referring to confidence in COVID-19 vaccines. These hesitancy profiles inform public health messaging approaches to effectively reach Twitter users with promise to shift or bolster vaccine attitudes.
Open AccessScaling Up the Discovery of Hesitancy Profiles by Identifying the Framing of Beliefs towards Vaccine Confidence in Twitter Discourse
Our study focused on the inference of the framing of confidence in the HPV vaccine throughout a collection of 422,078 tweets as well as the framing of confidence in the COVID-19 vaccines through a collection of 5,865,046 tweets. The vaccine confidence framings were inferred by using a novel Question/Answering framework enabling the derivation of a misinformation taxonomy as well as trust taxonomies for these two vaccines. These taxonomies, along with the analysis of vaccine literacy, the implied moral foundations and the tension between vaccine mandates and civil rights allowed us to discover several profiles of hesitancy for each vaccine across 138,779 Twitter users referring to confidence in HPV vaccine and 665,798 users referring to confidence in COVID-19 vaccines. These hesitancy profiles inform public health messaging approaches to effectively reach Twitter users with promise to shift or bolster vaccine attitudes.
- 1 October 2020
- Published by Oxford University Press (OUP) in Journal of the American Medical Informatics Association
- Vol. 27 (10) , 1556-1567
The impact of learning Unified Medical Language System knowledge embeddings in relation extraction from biomedical texts
Objective: We explored how knowledge embeddings (KEs) learned from the Unified Medical Language System (UMLS) Metathesaurus impact the quality of relation extraction on 2 diverse sets of biomedical texts. Materials and Methods: Two forms of KEs were learned for concepts and relation types from the UMLS Metathesaurus, namely lexicalized knowledge embeddings (LKEs) and unlexicalized KEs. A knowledge embedding encoder (KEE) enabled learning either LKEs or unlexicalized KEs as well as neural models capable of producing LKEs for mentions of biomedical concepts in texts and relation types that are not encoded in the UMLS Metathesaurus. This allowed us to design the relation extraction with knowledge embeddings (REKE) system, which incorporates either LKEs or unlexicalized KEs produced for relation types of interest and their arguments. Results: The incorporation of either LKEs or unlexicalized KE in REKE advances the state of the art in relation extraction on 2 relation extraction datasets: the 2010 i2b2/VA dataset and the 2013 Drug-Drug Interaction Extraction Challenge corpus. Moreover, the impact of LKEs is superior, achieving F1 scores of 78.2 and 82.0, respectively. Discussion: REKE not only highlights the importance of incorporating knowledge encoded in the UMLS Metathesaurus in a novel way, through 2 possible forms of KEs, but it also showcases the subtleties of incorporating KEs in relation extraction systems. Conclusions: Incorporating LKEs informed by the UMLS Metathesaurus in a relation extraction system operating on biomedical texts shows significant promise. We present the REKE system, which establishes new state-of-the-art results for relation extraction on 2 datasets when using LKEs.
- 1 October 2020
- Published by Oxford University Press (OUP) in Journal of the American Medical Informatics Association
- Vol. 27 (10) , 1556-1567
The impact of learning Unified Medical Language System knowledge embeddings in relation extraction from biomedical texts
Objective: We explored how knowledge embeddings (KEs) learned from the Unified Medical Language System (UMLS) Metathesaurus impact the quality of relation extraction on 2 diverse sets of biomedical texts. Materials and Methods: Two forms of KEs were learned for concepts and relation types from the UMLS Metathesaurus, namely lexicalized knowledge embeddings (LKEs) and unlexicalized KEs. A knowledge embedding encoder (KEE) enabled learning either LKEs or unlexicalized KEs as well as neural models capable of producing LKEs for mentions of biomedical concepts in texts and relation types that are not encoded in the UMLS Metathesaurus. This allowed us to design the relation extraction with knowledge embeddings (REKE) system, which incorporates either LKEs or unlexicalized KEs produced for relation types of interest and their arguments. Results: The incorporation of either LKEs or unlexicalized KE in REKE advances the state of the art in relation extraction on 2 relation extraction datasets: the 2010 i2b2/VA dataset and the 2013 Drug-Drug Interaction Extraction Challenge corpus. Moreover, the impact of LKEs is superior, achieving F1 scores of 78.2 and 82.0, respectively. Discussion: REKE not only highlights the importance of incorporating knowledge encoded in the UMLS Metathesaurus in a novel way, through 2 possible forms of KEs, but it also showcases the subtleties of incorporating KEs in relation extraction systems. Conclusions: Incorporating LKEs informed by the UMLS Metathesaurus in a relation extraction system operating on biomedical texts shows significant promise. We present the REKE system, which establishes new state-of-the-art results for relation extraction on 2 datasets when using LKEs.