Sentiment and Factual Transitions in Online Medical Forums
| dc.contributor.author | Bobicev, Victoria | |
| dc.contributor.author | Sokolova, Marina | |
| dc.contributor.author | Oakes, Michael | |
| dc.date.accessioned | 2017-12-11T15:05:37Z | |
| dc.date.available | 2017-12-11T15:05:37Z | |
| dc.date.issued | 2015 | |
| dc.identifier.isbn | 978-3-319-18356-5 | |
| dc.identifier.uri | http://hdl.handle.net/2436/620981 | |
| dc.description.abstract | This work studies sentiment and factual transitions on an online medical forum where users correspond in English. We work with discussions dedicated to reproductive technologies, an emotionally-charged issue. In several learning problems, we demonstrate that multi-class sentiment classification significantly improves when messages are represented by affective terms combined with sentiment and factual transition information (paired t-test, P=0.0011). | |
| dc.description.sponsorship | Self-funded | |
| dc.language.iso | en | |
| dc.publisher | Springer | |
| dc.subject | Sentiment Analysis | |
| dc.subject | Online Medical Forums | |
| dc.title | Sentiment and Factual Transitions in Online Medical Forums | |
| dc.type | Journal article | |
| dc.identifier.journal | Advances in Artificial Intelligence, 28th Canadian Conference on Artificial Intelligence | |
| refterms.dateFOA | 2018-08-20T13:41:06Z | |
| html.description.abstract | This work studies sentiment and factual transitions on an online medical forum where users correspond in English. We work with discussions dedicated to reproductive technologies, an emotionally-charged issue. In several learning problems, we demonstrate that multi-class sentiment classification significantly improves when messages are represented by affective terms combined with sentiment and factual transition information (paired t-test, P=0.0011). |
