Abstract
Modern Knowledge Graphs such as DBPedia contain significant information regarding Named Entities and the logical relationships which exist between them. Twitter on the other hand, contains important information on the popularity and frequency with which these entities are mentioned and discussed in combination with one another. In this paper we investigate whether these two sources of information can be used to complement and explain one another. In particular, we would like to know whether the logical relationships (a.k.a. semantic paths) which exist between pairs of known entities can help to explain the frequency with which those entities co-occur with one another in Twitter. To do this we train attranking function over semantic paths between pairs of entities. The aim of the ranker is to identify the path that most likely explains why a particular pair of entities have appeared together in a particular tweet. We train the ranking model using a number of lexical, graph-embedding and popularity-based features over semantic paths containing a single intermediate entity and demonstrate the efficacy of the model for determining why pairs of entities occur together in tweets.
| Language | English |
|---|---|
| Title of host publication | CIKM'17 |
| Subtitle of host publication | Proceedings of the 2017 ACM Conference on Information and Knowledge Management |
| Editors | Mark Sanderson, Ada Fu, Jimeng Sun, Shane Culpepper, Eric Lo, Joyce Ho, Debora Donato, Rakesh Agrawal, Yu Zheng, Carlos Castillo, Aixin Sun, Vincent S. Tseng, Chenliang Li |
| Place of Publication | New York NY USA |
| Publisher | Association for Computing Machinery (ACM) |
| Pages | 2351-2354 |
| Number of pages | 4 |
| ISBN (Print) | 9781450349185 |
| DOIs | |
| Publication status | Published - 6 Nov 2017 |
| Event | ACM International Conference on Information and Knowledge Management 2017 - Singapore, Singapore Duration: 6 Nov 2017 → 10 Nov 2017 Conference number: 26th |
Conference
| Conference | ACM International Conference on Information and Knowledge Management 2017 |
|---|---|
| Abbreviated title | CIKM 2017 |
| Country | Singapore |
| City | Singapore |
| Period | 6/11/17 → 10/11/17 |
Keywords
- DBPedia
- Importance ranking
- Information retrieval
- Knowledge graphs
- Machine learning
- Microblog
Cite this
}
Using knowledge graphs to explain entity co-occurrence in Twitter. / Wang, Yiwei; Carman, Mark James; Li, Yuan Fang.
CIKM'17: Proceedings of the 2017 ACM Conference on Information and Knowledge Management. ed. / Mark Sanderson; Ada Fu; Jimeng Sun; Shane Culpepper; Eric Lo; Joyce Ho; Debora Donato; Rakesh Agrawal; Yu Zheng; Carlos Castillo; Aixin Sun; Vincent S. Tseng; Chenliang Li. New York NY USA : Association for Computing Machinery (ACM), 2017. p. 2351-2354.Research output: Chapter in Book/Report/Conference proceeding › Conference Paper › Research
TY - GEN
T1 - Using knowledge graphs to explain entity co-occurrence in Twitter
AU - Wang, Yiwei
AU - Carman, Mark James
AU - Li, Yuan Fang
PY - 2017/11/6
Y1 - 2017/11/6
N2 - Modern Knowledge Graphs such as DBPedia contain significant information regarding Named Entities and the logical relationships which exist between them. Twitter on the other hand, contains important information on the popularity and frequency with which these entities are mentioned and discussed in combination with one another. In this paper we investigate whether these two sources of information can be used to complement and explain one another. In particular, we would like to know whether the logical relationships (a.k.a. semantic paths) which exist between pairs of known entities can help to explain the frequency with which those entities co-occur with one another in Twitter. To do this we train attranking function over semantic paths between pairs of entities. The aim of the ranker is to identify the path that most likely explains why a particular pair of entities have appeared together in a particular tweet. We train the ranking model using a number of lexical, graph-embedding and popularity-based features over semantic paths containing a single intermediate entity and demonstrate the efficacy of the model for determining why pairs of entities occur together in tweets.
AB - Modern Knowledge Graphs such as DBPedia contain significant information regarding Named Entities and the logical relationships which exist between them. Twitter on the other hand, contains important information on the popularity and frequency with which these entities are mentioned and discussed in combination with one another. In this paper we investigate whether these two sources of information can be used to complement and explain one another. In particular, we would like to know whether the logical relationships (a.k.a. semantic paths) which exist between pairs of known entities can help to explain the frequency with which those entities co-occur with one another in Twitter. To do this we train attranking function over semantic paths between pairs of entities. The aim of the ranker is to identify the path that most likely explains why a particular pair of entities have appeared together in a particular tweet. We train the ranking model using a number of lexical, graph-embedding and popularity-based features over semantic paths containing a single intermediate entity and demonstrate the efficacy of the model for determining why pairs of entities occur together in tweets.
KW - DBPedia
KW - Importance ranking
KW - Information retrieval
KW - Knowledge graphs
KW - Machine learning
KW - Microblog
KW - Twitter
UR - http://www.scopus.com/inward/record.url?scp=85037341536&partnerID=8YFLogxK
U2 - 10.1145/3132847.3133161
DO - 10.1145/3132847.3133161
M3 - Conference Paper
SN - 9781450349185
SP - 2351
EP - 2354
BT - CIKM'17
A2 - Sanderson, Mark
A2 - Fu, Ada
A2 - Sun, Jimeng
A2 - Culpepper, Shane
A2 - Lo, Eric
A2 - Ho, Joyce
A2 - Donato, Debora
A2 - Agrawal, Rakesh
A2 - Zheng, Yu
A2 - Castillo, Carlos
A2 - Sun, Aixin
A2 - Tseng, Vincent S.
A2 - Li, Chenliang
PB - Association for Computing Machinery (ACM)
CY - New York NY USA
ER -