Sentiment analysis is an active field of research, moving from the traditional algorithms that operated on complete documents to finegrained variants where aspects of the topic being discussed are extracted, as well as their associated sentiment. Recently, a move from traditional word-based approaches to concept-based approaches has started. In this work, it is shown by using a simple machine learning baseline, that concepts are useful as features within a machine learning framework. In all our experiments, the performance increases when including the conceptbased features.

dx.doi.org/10.1007/978-3-319-25518-7_19, hdl.handle.net/1765/90027
This work was funded by the European Commission 7th Framework Programme; grant id fp7/318159 - Making the Web an Exploratory for Geospatial Knowledge (GEOKNOW)
Erasmus University Rotterdam

Schouten, K.I.M, & Frasincar, F. (2015). The benefit of concept-based features for sentiment analysis. doi:10.1007/978-3-319-25518-7_19