English

DeepEmo: Learning and Enriching Pattern-Based Emotion Representations

Computation and Language 2018-04-25 v1 Information Retrieval

Abstract

We propose a graph-based mechanism to extract rich-emotion bearing patterns, which fosters a deeper analysis of online emotional expressions, from a corpus. The patterns are then enriched with word embeddings and evaluated through several emotion recognition tasks. Moreover, we conduct analysis on the emotion-oriented patterns to demonstrate its applicability and to explore its properties. Our experimental results demonstrate that the proposed techniques outperform most state-of-the-art emotion recognition techniques.

Keywords

Cite

@article{arxiv.1804.08847,
  title  = {DeepEmo: Learning and Enriching Pattern-Based Emotion Representations},
  author = {Elvis Saravia and Hsien-Chi Toby Liu and Yi-Shin Chen},
  journal= {arXiv preprint arXiv:1804.08847},
  year   = {2018}
}
R2 v1 2026-06-23T01:33:31.948Z