Téma: | Emotional detector model for text and/or speech
|
---|
Vedoucí: | Jan Holub
|
---|
Vypsáno jako: | Práce v týmu a její organizace
|
---|
Popis: | The goal of this project is to design a working prototype of emotional detector working either with text input or spoken (recorded) sentences. As these two options requires substantially different approach, two projects can be assigned.
|
---|
Pokyny: | The detector input will be either text or recorded speech. The detector core should evaluate it using developed text processing or signal processing functions and deliver the following outputs: emotion polarity estimation, emotion strenght estimation, estimation reliability.
|
---|
Literatura: | http://home.iitk.ac.in/~spranjal/cs365/projects/staffsJ.pdf
Melville, P., Gryc, W., Lawrence, R.: Sentiment Analysis of Blogs by Combining Lexical Knowledge with Text Classification. In: Proc. of SIGKDD 2009 (2009)
http://u.cs.biu.ac.il/~koppel/papers/neutrals-12.12.05.pdf
Pang et al.: Successfully applied a machine learning approach to classifying
sentiment for movie reviews
http://www.cs.cornell.edu/people/pabo/movie-review-data/
http://www.cs.jhu.edu/~mdredze/datasets/sentiment/index2.html
http://home.iitk.ac.in/~spranjal/cs365/projects/staffsJ.pdf
http://blog.datumbox.com/the-importance-of-neutral-class-in-sentiment-analysis/
http://u.cs.biu.ac.il/~koppel/papers/neutrals-12.12.05.pdf
|
---|
Realizace: | commented SW (Matlab, C++, Java )
|
---|
Vypsáno dne: | 17.02.2016
|
---|
Max. počet studentů: | 4
|
---|
Přihlášení studenti: | Aleš Svoboda,
Jan Prášek,
Jiří Pytela,
Leoš Mikulka
|
---|