Details
| Originalsprache | Englisch |
|---|---|
| Titel des Sammelwerks | WWW 2014 Companion - Proceedings of the 23rd International Conference on World Wide Web |
| Seiten | 569-570 |
| Seitenumfang | 2 |
| ISBN (elektronisch) | 9781450327459 |
| Publikationsstatus | Veröffentlicht - 7 Apr. 2014 |
| Veranstaltung | 23rd International Conference on World Wide Web, WWW 2014 - Seoul, Südkorea Dauer: 7 Apr. 2014 → 11 Apr. 2014 |
Abstract
User-generated content is a growing source of valuable infor- mation and its analysis can lead to a better understanding of the users needs and trends. In this paper, we leverage user feedback about YouTube videos for the task of affec- Tive video ranking. To this end, we follow a learning to rank approach, which allows us to compare the performance of different sets of features when the ranking task goes beyond mere relevance and requires an affective understanding of the videos. Our results show that, while basic video fea- Tures, such as title and tags, lead to effective rankings in an affective-less setup, they do not perform as good when dealing with an affective ranking task.
ASJC Scopus Sachgebiete
- Informatik (insg.)
- Computernetzwerke und -kommunikation
- Informatik (insg.)
- Software
Zitieren
- Standard
- Harvard
- Apa
- Vancouver
- BibTex
- RIS
WWW 2014 Companion - Proceedings of the 23rd International Conference on World Wide Web. 2014. S. 569-570.
Publikation: Beitrag in Buch/Bericht/Sammelwerk/Konferenzband › Aufsatz in Konferenzband › Forschung › Peer-Review
}
TY - GEN
T1 - Learning to rank for joy
AU - Orellana-Rodriguez, Claudia
AU - Nejdl, Wolfgang
AU - Diaz-Aviles, Ernesto
AU - Altingovde, Ismail Sengor
PY - 2014/4/7
Y1 - 2014/4/7
N2 - User-generated content is a growing source of valuable infor- mation and its analysis can lead to a better understanding of the users needs and trends. In this paper, we leverage user feedback about YouTube videos for the task of affec- Tive video ranking. To this end, we follow a learning to rank approach, which allows us to compare the performance of different sets of features when the ranking task goes beyond mere relevance and requires an affective understanding of the videos. Our results show that, while basic video fea- Tures, such as title and tags, lead to effective rankings in an affective-less setup, they do not perform as good when dealing with an affective ranking task.
AB - User-generated content is a growing source of valuable infor- mation and its analysis can lead to a better understanding of the users needs and trends. In this paper, we leverage user feedback about YouTube videos for the task of affec- Tive video ranking. To this end, we follow a learning to rank approach, which allows us to compare the performance of different sets of features when the ranking task goes beyond mere relevance and requires an affective understanding of the videos. Our results show that, while basic video fea- Tures, such as title and tags, lead to effective rankings in an affective-less setup, they do not perform as good when dealing with an affective ranking task.
KW - Sentiment analysis
KW - Socialmedia analytics
KW - Youtube
UR - http://www.scopus.com/inward/record.url?scp=84990924172&partnerID=8YFLogxK
U2 - 10.1145/2567948.2576961
DO - 10.1145/2567948.2576961
M3 - Conference contribution
AN - SCOPUS:84990924172
SP - 569
EP - 570
BT - WWW 2014 Companion - Proceedings of the 23rd International Conference on World Wide Web
T2 - 23rd International Conference on World Wide Web, WWW 2014
Y2 - 7 April 2014 through 11 April 2014
ER -