Sentiment-Analysis

Resources for sentiment analysis, sentiment classification, and emotions classification (Affective Text)

Tasks related with sentiment

• Sentiment Analysis : clssify the text to postive, negative, (and neutral) and use the information as a features - predict sales, stock market, recommendations
• Sentiment classification : predict the sentiment itself, focus on fine-grained datasets or improving model structures
• Emotions classification : understand emotions beyond sentiment, recently gets more attentions.

Papers related with emotions

• GoEmotions: A Dataset of Fine-Grained Emotions (ACL 2020) paper | dataset

  • Demszky, Dorottya and Movshovitz-Attias, Dana and Ko, Jeongwoo and Cowen, Alan and Nemade, Gaurav and Ravi, Sujith

• Hashtags, Emotions, and Comments: A Large-Scale Dataset to Understand Fine-Grained Social Emotions to Online Topics (EMNLP 2020) paper | dataset

  • Keyang Ding, Jing Li, Yuji Zhang

• EmoTag1200 : Understanding the Association between Emojis and Emotions (EMNLP 2020) paper

  • Abu Awal Md Shoeb, Gerard de Melo

• CANCEREMO : A Dataset for Fine-Grained Emotion Detection (EMNLP 2020) paper

  • Tiberiu Sosea, Cornelia Caragea

• CARER: Contextualized Affect Representations for Emotion Recognition (EMNLP 2018) paper | dataset

  • Elvis Saravia, Hsien-Chi Toby Liu, Yen-Hao Huang, Junlin Wu, Yi-Shin Chen

• The Hourglass Model Revisited (IEEE Intelligent Systems 2020) paper

• An Analysis of Annotated Corpora for Emotion Classification in Text - Unified Dataset (COLING 2018) Paper| Code

  • Laura-Ana-Maria Bostan and Roman Klinger

• EmoNet: Fine-Grained Emotion Detection with Gated Recurrent Neural Networks (ACL 2017) paper | code-pytorch

  • Muhammad Abdul-Mageed, Lyle Ungar
  • 1.6M tweet / 24 emotion labels / using Plutchik / Distant supervision approach (a proxy)

• Using millions of emoji occurrences to learn any-domain representations for detecting sentiment, emotion and sarcasm DeepMoji (EMNLP 2017) Paper

  • Bjarke Felbo, Alan Mislove, Anders Søgaard, Iyad Rahwan, Sune Lehmann
  • 1,246M tweets, 64 Emojis, 8 benchmark set / Extending the distant supervision approach

• Annotation, Modelling and Analysis of Fine-Grained Emotions on a Stance and Sentiment Detection Corpus SSEC (WASSA 2017) Paper

  • Hendrik Schuff, Jeremy Barnes, Julian Mohme, Sebastian Padó, Roman Klinger
  • 5k Tweets, using Pluchik, consider target

• IMS at EmoInt-2017:Emotion Intensity Prediction with Affective Norms,Automatically Extended Resources and Deep Learning EmoInt - SemEval 2017 Paper

  • Maximilian Köper, Evgeny Kim, Roman Klinger
  • 7k tweets, using Ekman (anger, joy, sadness, fear)

• EmoTweet-28: A Fine-Grained Emotion Corpus for Sentiment Analysis (LREC 2016) Paper

  • Jasy Suet Yan Liew, Howard R. Turtle, Elizabeth D. Liddy
  • 15k tweets, 28 emotion labels / 4 emotion facets (Valence, Arousal, Emotion Tag, Emo cues)

• Building Large-Scale Twitter-Specific Sentiment Lexicon : A Representation Learning Approach (COLING 2014) Paper

  • Duyu Tang, Furu Wei, Bing Qin, Ming Zhou, Ting Liu
  • 10M Tweets, Seed expansion with Urban Dictionary