Emotion‐aware polarity lexicons for Twitter sentiment analysis

Abstract

Theoretical frameworks in psychology map the relationships between emotions and sentiments. In this paper we study the role of such mapping for computational emotion detection from text (e.g. social media) with a aim to understand the usefulness of an emotion-rich corpus of documents (e.g. tweets) to learn polarity lexicons for sentiment analysis. We propose two different methods that leverage a corpus of emotion-labelled tweets to learn word-polarity lexicons. The proposed methods model the emotion corpus using a generative unigram mixture model (UMM), combined with the emotion-sentiment mapping proposed in Psychology for automated generation of word-polarity lexicons that capture emotion-rich vocabulary. We comparatively evaluate the quality of the proposed mixture model in learning emotion-aware sentiment lexicons with those generated using supervised latent dirichlet allocation (sLDA) and word-document frequency (WDF) statistics. Sentiment analysis experiments on benchmark Twitter data sets confirm the quality of our proposed lexicons. Further a comparative analysis with sLDA, WDF based emotion-aware lexicons and standard sentiment lexicons that are agnostic to emotion knowledge suggest that the proposed lexicons lead to a significantly better performance in both sentiment classification and sentiment intensity prediction tasks.

The positive energy of netizens: development and application of fine-grained sentiment lexicon and emotional intensity model

“…Furthermore, it is difficult to get a complete result by using emotional dictionaries or intensity models alone if we need to analyze the characteristics of Weibo users' emotional expressions. Bandhakavi et al ( 2021 ) pointed out that when studying emotion expression, researchers should consider not only the categories of emotion but also the intensity of emotion. Given that previous studies have rarely considered the categories and intensities of emotions in a comprehensive manner, this study addresses this shortcoming by constructing two research tools for measuring netizens' emotional expression with high reliability and validity for the domestic study of Chinese text analysis.…”

Identification of Emotional Spectrums of Patients Taking an Erectile Dysfunction Medication: Ontology-Based Emotion Analysis of Patient Medication Reviews on Social Media

“…This study adopted the Parrot emotion model [ 29 ], which has been previously used for emotion analysis of social media data [ 30 , 31 ]. Parrot’s model classifies emotions into 3 levels: primary, secondary, and tertiary.…”

Enriched Latent Dirichlet Allocation for Sentiment Analysis

“…On the basis of the traditional RJST model in which document collections are exchangeable, the SRJST model incorporates the Markov assumption among daily collected documents, and its control chart is consequently more sensitive to extremely small shifts in the document level topics and sentiments. In Bandhakavi, Wiratunga, Massie, and P (), the authors study the mapping proposed in psychology between emotions and sentiments, from a computational modelling perspective in order to establish the role of an emotion corpus for sentiment analysis. The authors propose two different methods to extract lexicons for Twitter sentiment analysis from an emotion‐labelled Twitter corpus.…”