Abstract
This paper describes a probabilistic latent variable model that is designed to detect human values such as justice or freedom that a writer has sought to reflect or appeal to when participating in a public debate. The proposed model treats the words in a sentence as having been chosen based on specific values; values reflected by each sentence are then estimated by aggregating values associated with each word. The model can determine the human values for the word in light of the influence of the previous word. This design choice was motivated by syntactic structures such as noun+noun, adjective+noun, and verb+adjective. The classifier based on the model was evaluated on a test collection containing 102 manually annotated documents focusing on one contentious political issue - Net neutrality, achieving the highest reported classification effectiveness for this task. We also compared our proposed classifier with human second anno-tator. As a result, the proposed classifier effectiveness is statistically comparable with human annotators.
| Original language | English |
|---|---|
| Title of host publication | CIKM 2014 - Proceedings of the 2014 ACM International Conference on Information and Knowledge Management |
| Publisher | Association for Computing Machinery, Inc |
| Pages | 1489-1498 |
| Number of pages | 10 |
| ISBN (Electronic) | 9781450325981 |
| DOIs | |
| Publication status | Published - Nov 3 2014 |
| Event | 23rd ACM International Conference on Information and Knowledge Management, CIKM 2014 - Shanghai, China Duration: Nov 3 2014 → Nov 7 2014 |
Publication series
| Name | CIKM 2014 - Proceedings of the 2014 ACM International Conference on Information and Knowledge Management |
|---|
Other
| Other | 23rd ACM International Conference on Information and Knowledge Management, CIKM 2014 |
|---|---|
| Country | China |
| City | Shanghai |
| Period | 11/3/14 → 11/7/14 |
Fingerprint
All Science Journal Classification (ASJC) codes
- Information Systems and Management
- Computer Science Applications
- Information Systems
Cite this
A word-scale probabilistic latent variable model for detecting human values. / Takayama, Yasuhiro; Tomiura, Yoichi; Ishita, Emi; Oard, Douglas W.; Fleischmann, Kenneth R.; Cheng, An Shou.
CIKM 2014 - Proceedings of the 2014 ACM International Conference on Information and Knowledge Management. Association for Computing Machinery, Inc, 2014. p. 1489-1498 (CIKM 2014 - Proceedings of the 2014 ACM International Conference on Information and Knowledge Management).Research output: Chapter in Book/Report/Conference proceeding › Conference contribution
}
TY - GEN
T1 - A word-scale probabilistic latent variable model for detecting human values
AU - Takayama, Yasuhiro
AU - Tomiura, Yoichi
AU - Ishita, Emi
AU - Oard, Douglas W.
AU - Fleischmann, Kenneth R.
AU - Cheng, An Shou
PY - 2014/11/3
Y1 - 2014/11/3
N2 - This paper describes a probabilistic latent variable model that is designed to detect human values such as justice or freedom that a writer has sought to reflect or appeal to when participating in a public debate. The proposed model treats the words in a sentence as having been chosen based on specific values; values reflected by each sentence are then estimated by aggregating values associated with each word. The model can determine the human values for the word in light of the influence of the previous word. This design choice was motivated by syntactic structures such as noun+noun, adjective+noun, and verb+adjective. The classifier based on the model was evaluated on a test collection containing 102 manually annotated documents focusing on one contentious political issue - Net neutrality, achieving the highest reported classification effectiveness for this task. We also compared our proposed classifier with human second anno-tator. As a result, the proposed classifier effectiveness is statistically comparable with human annotators.
AB - This paper describes a probabilistic latent variable model that is designed to detect human values such as justice or freedom that a writer has sought to reflect or appeal to when participating in a public debate. The proposed model treats the words in a sentence as having been chosen based on specific values; values reflected by each sentence are then estimated by aggregating values associated with each word. The model can determine the human values for the word in light of the influence of the previous word. This design choice was motivated by syntactic structures such as noun+noun, adjective+noun, and verb+adjective. The classifier based on the model was evaluated on a test collection containing 102 manually annotated documents focusing on one contentious political issue - Net neutrality, achieving the highest reported classification effectiveness for this task. We also compared our proposed classifier with human second anno-tator. As a result, the proposed classifier effectiveness is statistically comparable with human annotators.
UR - http://www.scopus.com/inward/record.url?scp=84937604507&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=84937604507&partnerID=8YFLogxK
U2 - 10.1145/2661829.2661966
DO - 10.1145/2661829.2661966
M3 - Conference contribution
AN - SCOPUS:84937604507
T3 - CIKM 2014 - Proceedings of the 2014 ACM International Conference on Information and Knowledge Management
SP - 1489
EP - 1498
BT - CIKM 2014 - Proceedings of the 2014 ACM International Conference on Information and Knowledge Management
PB - Association for Computing Machinery, Inc
ER -