Mixture of Topic-Based Distributional Semantic and Affective Models


Typically, Distributional Semantic Models (DSMs) estimate semantic similarity between words using a single-model, where the multiple senses of polysemous words are conflated in a single representation. Similarly, in textual affective analysis tasks, ambiguous words are usually not treated differently when estimating word affective scores. In this work, a semantic mixture model is proposed enabling the combination of word similarity scores estimated across multiple topic-specific DSMs (TDSMs). Based on the assumption that semantic similarity implies affective similarity, we extend this model to perform sentence-level affect estimation. The proposed model outperforms the baseline approach achieving state-of-the-art results for semantic similarity estimation and sentence-level polarity detection.

Proceeding of the 12th IEEE International Conference on Semantic Computing