Titulo Estágio
Spatiotemporal Emotional Maps from Opinion Mining and Sentiment Analysis of Texts
Área Tecnológica
Inteligência Artificial
Local do Estágio
DEI-FCTUC
Enquadramento
Sentiment analysis of text has recently become a very popular
tool for making opinion mining and products review. A basic task in sentiment analysis is classifying the polarity of a given text at the document, sentence, or feature/aspect level to know whether the expressed opinion in a document, a sentence or an entity feature/aspect is positive, negative, or neutral. Advanced, "beyond polarity" sentiment classification looks, for instance, at emotional states such as "angry," "sad," and "happy”.
Objetivo
The goal of this project is to make use of sentiment analysis to produce the emotional states of texts that may be geographical and/or temporal distributed, and then visualize those emotional states appropriately. The methodology includes:
- training a classifier with a previously built dataset of emotional tagged texts (this dataset will be provided)
- apply the classifier to a text (e.g., a book, tweets, etc.)
- build a spatiotemporal visualization (a kind of emotional map) of the text based on the classifier output
Plano de Trabalhos - Semestre 1
- State of the Art [Sept – Nov]
- Analysis and Specification [Dec]
- Definition of System Requirements
- Use Case Definition
- Design and Specification
- Prototype Development [Dec – Feb]
- Thesis Proposal Writing [Dec – Feb]
Plano de Trabalhos - Semestre 2
- Prototype Improvement [Mar – May]
- Experimental Tests [Jun – Jul]
- Functional Tests
- Performance Tests
- Thesis Writing [Jun – Jul]
Condições
The work will be developed in one of the labs of the Cognitive and Media Systems.
Observações
References
Aman, S., and Szpakowicz, S. Identifying expressions of emotion in text. In TSD’07 (2007), pp. 196–205.
Bollen, J., Mao, H., and Zeng, X.-J. Twitter mood predicts the stock market. CoRR (2010), 1–1.
Choi, H., and Varian, H. Predicting the present with google trends. Tech. rep., Google Inc, 2011.
McCallum, A. K. Mallet: A machine learning for language toolkit., 2002.
Picard, R. W. Affective Computing, vol. 136. MIT Press, 1997.
Popescu, A. M., and Etzioni, O. Extracting product features and opinions from reviews. In HLT/EMNLP’05 (2005), pp. 1–1.
Strapparava, C., and Mihalcea, R. Learning to identify emotions in text. In SAC’08 (2008), pp. 1556–1560.
Orientador
Luis Macedo
macedo@dei.uc.pt 📩