Harnessing Twitter "Big Data" for Automatic Emotion Identification

By Wenbo Wang, Lu Chen, Krishnaprasad Thirunarayan, Amit P. Sheth. 2012 International Conference on Privacy, Security, Risk and Trust and 2012 International Confernece on Social Computing, 2012

387 citations recorded by the source corpus.

Subfields: Artificial Intelligence

View Paper: https://www.semanticscholar.org/paper/773dd632f52355eb4f7cb61ae160a10e7acce001

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

Citations in the corpus

Predictive Analysis on Twitter: Techniques and Applications (2018, background): “[6] predicted seven categorical emotions from the content of tweets using 131 emotion hashtags and utilizing the features such as n-grams, emotion lexicon words, part-of-speech tags, and ngram positions.”
EmoNet: Fine-Grained Emotion Detection with Gated Recurrent Neural Networks (2017, methodology): “As pointed out earlier, (Wang et al., 2012) randomly sample a set of 400 tweets from their data and human-label as relevant/irrelevant, as a way to verify the distant super-vision approach with the quality assurance heuristics they employ.”
CARER: Contextualized Affect Representations for Emotion Recognition (2018, methodology): “Emotion Lexica: Several works use hand-crafted features and statistics-based approaches to train emotion recognition models (Blitzer et al., 2007; Wang et al., 2012; Roberts et al., 2012; Qadir and Riloff, 2013; Volkova et al., 2013; Becker et al., 2017; Saravia et al., 2016a).”
A Systematic Review of Emoji: Current Research and Future Perspectives (2019, methodology): “The machine learning method refers to train sentiment classifiers based on a corpus in order to analyze the sentiments of text (Wang et al., 2012).”
Predicting Users' Motivations behind Location Check-Ins and Utility Implications of Privacy Protection Mechanisms (2015, methodology): “2) Unstructured Text Features: Based on prior studies in the analysis of short texts, we extract the following high-level text-related features from each check-in: the emotion (such as joy or anger) [33] and the sentiment (such as positive or negative) [10].”
One-step and Two-step Classification for Abusive Language Detection on Twitter (2017, methodology): “Waseem (2016) used logistic regression with n-grams and user-specific features such as gender and location.”
GoEmotions: A Dataset of Fine-Grained Emotions (2020, background): “Other datasets are automatically weakly-labeled, based on emotion-related hashtags on Twitter (Wang et al., 2012; Abdul-Mageed and Ungar, 2017).”
SemEval-2019 Task 3: EmoContext Contextual Emotion Detection in Text (2019, background): “Hasan et al. (2014), Purver and Battersby (2012), Suttles and Ide (2013) and Wang et al. (2012) have also harnessed cues from emoticons and hashtags.”
Domain-Specific Use Cases for Knowledge-Enabled Social Media Analysis (2018, background): “Various Natural Language Processing (NLP) techniques have been deployed for opinion mining [9, 27], sentiment analysis [10, 20], emotion analysis [17, 39], metadata extraction [1] and user group’s characterization [28].”