KOPS - Das Institutionelle Repositorium der Universität Konstanz

Opinion Marks : A Human-Based Computation Approach to Instill Structure into Unstructured Text on the Web

Opinion Marks : A Human-Based Computation Approach to Instill Structure into Unstructured Text on the Web

Zitieren

Dateien zu dieser Ressource

Dateien Größe Format Anzeige

Zu diesem Dokument gibt es keine Dateien.

KWON, Bum Chul, Jaegul CHOO, Sung-Hee KIM, Daniel KEIM, Haesun PARK, Ji Soo YI, 2015. Opinion Marks : A Human-Based Computation Approach to Instill Structure into Unstructured Text on the Web. KDD 2015 Workshop on Interactive Data Exploration and Analytics (IDEA’15). Sydney, 13. Aug 2015. In: POLO CHAU, , ed. and others. Proceedings of the ACM SIGKDD Workshop on Interactive Data Exploration and Analytics Permission. KDD 2015 Workshop on Interactive Data Exploration and Analytics (IDEA’15). Sydney, 13. Aug 2015. New York:ACM, pp. 47-55

@inproceedings{Kwon2015Opini-32597, title={Opinion Marks : A Human-Based Computation Approach to Instill Structure into Unstructured Text on the Web}, year={2015}, address={New York}, publisher={ACM}, booktitle={Proceedings of the ACM SIGKDD Workshop on Interactive Data Exploration and Analytics Permission}, pages={47--55}, editor={Polo Chau}, author={Kwon, Bum Chul and Choo, Jaegul and Kim, Sung-Hee and Keim, Daniel and Park, Haesun and Yi, Ji Soo} }

Kim, Sung-Hee Yi, Ji Soo Despite recent improvements in computational approaches such as<br />machine learning, natural language processing, and computational<br />linguistics, making a computer understand human-generated unstructured<br />text still remains a difficult problem to solve. To alleviate<br />the challenges, we propose an approach called “Opinion Marks,”<br />which enables writers to mark positive and negative aspects of a<br />topic on their own text. In addition, Opinion Marks incorporates an<br />automatic marking suggestion algorithm to offload a user’s marking<br />effort. The phrases marked with Opinion Marks can be further<br />used to clarify the sentiments of other text in a similar context.<br />We implemented Opinion Marks at a question answering website<br />http://caniask.net. To test the efficacy of Opinion Marks, we<br />conducted a crowdsourced experiment with 144 participants in a<br />between-subject design under three different conditions: 1) human<br />marking only; 2) machine marking only (automatic marking suggestion);<br />and 3) human-machine collaboration (Opinion Marks).<br />This study revealed that Opinion Marks significantly improves the<br />quality of marked phrases and usability of the system. Park, Haesun eng 2016-01-15T08:33:21Z Choo, Jaegul 2016-01-15T08:33:21Z Opinion Marks : A Human-Based Computation Approach to Instill Structure into Unstructured Text on the Web Kim, Sung-Hee Keim, Daniel Park, Haesun 2015 Choo, Jaegul Kwon, Bum Chul Yi, Ji Soo Keim, Daniel Kwon, Bum Chul

Das Dokument erscheint in:

KOPS Suche


Stöbern

Mein Benutzerkonto