AffectiveSpace 2: Enabling Affective Intuition for Concept-Level Sentiment Analysis

Erik Cambria, Jie Fu, Federica Bisio, Soujanya Poria

AAAI 2015 pp. 508-514

doi:10.1609/AAAI.V29I1.9230 /aaai/2015/cambria2015aaai-affectivespace/

Abstract

Predicting the affective valence of unknown multi-word expressions is key for concept-level sentiment analysis. AffectiveSpace 2 is a vector space model, built by means of random projection, that allows for reasoning by analogy on natural language con- cepts. By reducing the dimensionality of affec- tive common-sense knowledge, the model allows semantic features associated with concepts to be generalized and, hence, allows concepts to be intu- itively clustered according to their semantic and affective relatedness. Such an affective intuition (so called because it does not rely on explicit fea- tures, but rather on implicit analogies) enables the inference of emotions and polarity conveyed by multi-word expressions, thus achieving efficient concept-level sentiment analysis.

PDF AAAI Semantic Scholar

Cite

Text

Cambria et al. "AffectiveSpace 2: Enabling Affective Intuition for Concept-Level Sentiment Analysis." AAAI Conference on Artificial Intelligence, 2015. doi:10.1609/AAAI.V29I1.9230

Markdown

[Cambria et al. "AffectiveSpace 2: Enabling Affective Intuition for Concept-Level Sentiment Analysis." AAAI Conference on Artificial Intelligence, 2015.](https://mlanthology.org/aaai/2015/cambria2015aaai-affectivespace/) doi:10.1609/AAAI.V29I1.9230

BibTeX

@inproceedings{cambria2015aaai-affectivespace,
  title     = {{AffectiveSpace 2: Enabling Affective Intuition for Concept-Level Sentiment Analysis}},
  author    = {Cambria, Erik and Fu, Jie and Bisio, Federica and Poria, Soujanya},
  booktitle = {AAAI Conference on Artificial Intelligence},
  year      = {2015},
  pages     = {508-514},
  doi       = {10.1609/AAAI.V29I1.9230},
  url       = {https://mlanthology.org/aaai/2015/cambria2015aaai-affectivespace/}
}