Details
| Originalsprache | Englisch |
|---|---|
| Titel des Sammelwerks | 45th International ACM Conference on Research and Development in Information Retrieval (SIGIR 2022) |
| Herausgeber/-innen | Enrique Amigó, Pablo Castells, Julio Gonzalo, Ben Carterette, J. Shane Culpepper, Gabriella Kazai |
| Seiten | 2393-2399 |
| Seitenumfang | 7 |
| ISBN (elektronisch) | 9781450387323 |
| Publikationsstatus | Veröffentlicht - 7 Juli 2022 |
| Extern publiziert | Ja |
Abstract
We present an approach to identify argumentative questions among web search queries. Argumentative questions ask for reasons to support a certain stance on a controversial topic, such as ''Should marijuana be legalized?'' Controversial topics entail opposing stances, and hence can be supported or opposed by various arguments. Argumentative questions pose a challenge for search engines since they should be answered with both pro and con arguments in order to not bias a user toward a certain stance. To further analyze the problem, we sampled questions about 19 controversial topics from a large Yandex search log and let human annotators label them as one of factual, method, or argumentative. The result is a collection of 39,340 labeled questions, 28% of which are argumentative, demonstrating the need to develop dedicated systems for this type of questions. A comparative analysis of the three question types shows that asking for reasons and predictions are among the most important features of argumentative questions. To demonstrate the feasibility of the classification task, we developed a BERT-based classifier to map questions to the question types, reaching a promising macro-averaged F>sub>1-score of 0.78.
ASJC Scopus Sachgebiete
- Informatik (insg.)
- Software
- Informatik (insg.)
- Information systems
- Informatik (insg.)
- Computergrafik und computergestütztes Design
Zitieren
- Standard
- Harvard
- Apa
- Vancouver
- BibTex
- RIS
45th International ACM Conference on Research and Development in Information Retrieval (SIGIR 2022). Hrsg. / Enrique Amigó; Pablo Castells; Julio Gonzalo; Ben Carterette; J. Shane Culpepper; Gabriella Kazai. 2022. S. 2393-2399.
Publikation: Beitrag in Buch/Bericht/Sammelwerk/Konferenzband › Aufsatz in Konferenzband › Forschung › Peer-Review
}
TY - GEN
T1 - Identifying Argumentative Questions in Web Search Logs
AU - Ajjour, Yamen
AU - Braslavski, Pavel
AU - Bondarenko, Alexander
AU - Stein, Benno
N1 - Publisher Copyright: © 2022 ACM.
PY - 2022/7/7
Y1 - 2022/7/7
N2 - We present an approach to identify argumentative questions among web search queries. Argumentative questions ask for reasons to support a certain stance on a controversial topic, such as ''Should marijuana be legalized?'' Controversial topics entail opposing stances, and hence can be supported or opposed by various arguments. Argumentative questions pose a challenge for search engines since they should be answered with both pro and con arguments in order to not bias a user toward a certain stance. To further analyze the problem, we sampled questions about 19 controversial topics from a large Yandex search log and let human annotators label them as one of factual, method, or argumentative. The result is a collection of 39,340 labeled questions, 28% of which are argumentative, demonstrating the need to develop dedicated systems for this type of questions. A comparative analysis of the three question types shows that asking for reasons and predictions are among the most important features of argumentative questions. To demonstrate the feasibility of the classification task, we developed a BERT-based classifier to map questions to the question types, reaching a promising macro-averaged F>sub>1-score of 0.78.
AB - We present an approach to identify argumentative questions among web search queries. Argumentative questions ask for reasons to support a certain stance on a controversial topic, such as ''Should marijuana be legalized?'' Controversial topics entail opposing stances, and hence can be supported or opposed by various arguments. Argumentative questions pose a challenge for search engines since they should be answered with both pro and con arguments in order to not bias a user toward a certain stance. To further analyze the problem, we sampled questions about 19 controversial topics from a large Yandex search log and let human annotators label them as one of factual, method, or argumentative. The result is a collection of 39,340 labeled questions, 28% of which are argumentative, demonstrating the need to develop dedicated systems for this type of questions. A comparative analysis of the three question types shows that asking for reasons and predictions are among the most important features of argumentative questions. To demonstrate the feasibility of the classification task, we developed a BERT-based classifier to map questions to the question types, reaching a promising macro-averaged F>sub>1-score of 0.78.
KW - argumentative questions
KW - crowdsourcing
KW - web search log
UR - http://www.scopus.com/inward/record.url?scp=85135005168&partnerID=8YFLogxK
U2 - 10.1145/3477495.3531864
DO - 10.1145/3477495.3531864
M3 - Conference contribution
SP - 2393
EP - 2399
BT - 45th International ACM Conference on Research and Development in Information Retrieval (SIGIR 2022)
A2 - Amigó, Enrique
A2 - Castells, Pablo
A2 - Gonzalo, Julio
A2 - Carterette, Ben
A2 - Culpepper, J. Shane
A2 - Kazai, Gabriella
ER -