File Download
Supplementary
-
Citations:
- Appears in Collections:
Conference Paper: Time-sensitive opinion mining for prediction
Title | Time-sensitive opinion mining for prediction |
---|---|
Authors | |
Issue Date | 2015 |
Citation | The 29th AAAI Conference on Artificial Intelligence (AAAI-15), Austin, TX., 25-30 January 2015. In Conference Proceedings, 2015, p. 4214-4215 How to Cite? |
Abstract | Users commonly use Web 2.0 platforms to post their opinions and their predictions about future events (e.g., the movement of astock). Therefore, opinion mining can be used as a tool for predicting future events. Previous work on opinion mining extracts from the text only the polarity of opinions as sentiment indicators. We observe that a typical opinion post also contains temporal references which can improve prediction. This short paper presents our preliminary work on extracting reference time tagsand integrating them into an opinion mining model, in order to improvethe accuracy of future event prediction. We conduct anexperimental evaluation using a collection of microblogs posted by investors to demonstrate the effectiveness of our approach. |
Persistent Identifier | http://hdl.handle.net/10722/213622 |
DC Field | Value | Language |
---|---|---|
dc.contributor.author | Tu, W | - |
dc.contributor.author | Cheung, D | - |
dc.contributor.author | Mamoulis, N | - |
dc.date.accessioned | 2015-08-07T03:52:44Z | - |
dc.date.available | 2015-08-07T03:52:44Z | - |
dc.date.issued | 2015 | - |
dc.identifier.citation | The 29th AAAI Conference on Artificial Intelligence (AAAI-15), Austin, TX., 25-30 January 2015. In Conference Proceedings, 2015, p. 4214-4215 | - |
dc.identifier.uri | http://hdl.handle.net/10722/213622 | - |
dc.description.abstract | Users commonly use Web 2.0 platforms to post their opinions and their predictions about future events (e.g., the movement of astock). Therefore, opinion mining can be used as a tool for predicting future events. Previous work on opinion mining extracts from the text only the polarity of opinions as sentiment indicators. We observe that a typical opinion post also contains temporal references which can improve prediction. This short paper presents our preliminary work on extracting reference time tagsand integrating them into an opinion mining model, in order to improvethe accuracy of future event prediction. We conduct anexperimental evaluation using a collection of microblogs posted by investors to demonstrate the effectiveness of our approach. | - |
dc.language | eng | - |
dc.relation.ispartof | Proceedings of the Twenty-Ninth AAAI Conference on Artificial Intelligence | - |
dc.title | Time-sensitive opinion mining for prediction | - |
dc.type | Conference_Paper | - |
dc.identifier.email | Cheung, D: dcheung@cs.hku.hk | - |
dc.identifier.email | Mamoulis, N: nikos@cs.hku.hk | - |
dc.identifier.authority | Cheung, D=rp00101 | - |
dc.identifier.authority | Mamoulis, N=rp00155 | - |
dc.description.nature | postprint | - |
dc.identifier.hkuros | 246259 | - |
dc.identifier.spage | 4214 | - |
dc.identifier.epage | 4215 | - |