Unleashing the Potential of Argument Mining for IS Research: A Systematic Review and Research Agenda
Loading...
Paper Number
2358
Paper Type
Complete
Description
Argument mining (AM) represents the unique use of natural language processing (NLP) techniques to extract arguments from unstructured data automatically. Despite expanding on commonly used NLP techniques, such as sentiment analysis, AM has hardly been applied in information systems (IS) research yet. Consequentially, knowledge about the potentials for the usage of AM on IS use cases appears to be still limited. First, we introduce AM and its current usage in fields beyond IS. To address this research gap, we conducted a systematic literature review on IS literature to identify IS use cases that can potentially be extended with AM. We develop eleven text-based IS research topics that provide structure and context to the use cases and their AM potentials. Finally, we formulate a novel research agenda to guide both researchers and practitioners to design, compare and evaluate the use of AM for text-based applications and research streams in IS.
Recommended Citation
Weingart, Pablo; Wambsganss, Thiemo; and Söllner, Matthias, "Unleashing the Potential of Argument Mining for IS Research: A Systematic Review and Research Agenda" (2022). ICIS 2022 Proceedings. 11.
https://aisel.aisnet.org/icis2022/data_analytics/data_analytics/11
Unleashing the Potential of Argument Mining for IS Research: A Systematic Review and Research Agenda
Argument mining (AM) represents the unique use of natural language processing (NLP) techniques to extract arguments from unstructured data automatically. Despite expanding on commonly used NLP techniques, such as sentiment analysis, AM has hardly been applied in information systems (IS) research yet. Consequentially, knowledge about the potentials for the usage of AM on IS use cases appears to be still limited. First, we introduce AM and its current usage in fields beyond IS. To address this research gap, we conducted a systematic literature review on IS literature to identify IS use cases that can potentially be extended with AM. We develop eleven text-based IS research topics that provide structure and context to the use cases and their AM potentials. Finally, we formulate a novel research agenda to guide both researchers and practitioners to design, compare and evaluate the use of AM for text-based applications and research streams in IS.
When commenting on articles, please be friendly, welcoming, respectful and abide by the AIS eLibrary Discussion Thread Code of Conduct posted here.
Comments
13-DataAnalytics