Supposing there is a hotel review and generally Sentiment analysis identifies aspects from the review and give them a sentiment score, mainly based on linguistic details.
I want to know if there are any researches that attempt to give an importance to these aspects based on factors like reviewer's travel purpose (eg: business, leisure etc) or others.
Hi,
Sentiment analysis involves aspect extraction and categorization, sentiment lexicon analysis and summarizing aspects for specific product or hotels etc. There are different methods for ranking aspects but most of them are frequency based i.e. most occurrence of aspect most important is it or more positive the most important. Here are few papers for ranking of aspects may be helpful for you.
Eirinaki, M.; Pisal, S. & Singh, J. Feature-based opinion mining and ranking Journal of Computer and System Sciences, Elsevier, 2012, 78, 1175-1184
Bancken, W.; Alfarone, D. & Davis, J. Automatically detecting and rating product aspects from textual customer reviews (To appear in) Proceedings of DMNLP Workshop at ECML/PKDD, 2014
Deng, Z.-H.; Luo, K.-H. & Yu, H.-L. A study of supervised term weighting scheme for sentiment analysis Expert Systems with Applications, Elsevier, 2014, 41, 3506-3513
Marrese-Taylor, E.; Velásquez, J. D. & Bravo-Marquez, F. A novel deterministic approach for aspect-based opinion mining in tourism products reviews Expert Systems with Applications, Elsevier, 2014, 41, 7764-7775
Also look into topic modeling and visit Dr. Bing liu's site, it contains extensive work and review books on sentiment analysis. Hope this helps.
- Badges
- Science topic
- Similar topics
- Linguistics