Publications, data, talks, visualizations by area (papers within each area are organized reverse chronologically)
Publications for areas marked with a * are interspersed within sentiment analysis and emotion analysis; clicking on them leads to separate dedicated pages that present only the relevant information.
Data for download (The publication page also provides data associated with individual publications.)
Word-association lexicons for sentiment and emotion
(Note: A table summarizing various word-association lexicons can be found here.)
Data visualization and information sonification demos
- TransProse: Converting Text to Music. Hannah Davis and Saif M. Mohammad.
A system that takes as input classic English novels and generates music that captures the flow of emotions in it.
- An Interactive Visualizer for the NRC Emotion Lexicon
The NRC Emotion Lexicon is a list of English words and their associations with eight basic emotions (anger, fear, anticipation, trust, surprise, sadness, joy, and disgust) and two sentiments (negative and positive). The annotations were manually done by crowdsourcing.
- Interactive Visualizers for Sentiment Composition Lexicons
Sentiment composition is the determining of sentiment of a multi-word linguistic unit, such as a phrase or a sentence, based on its constituents. We present two visualizations: (1) exploring sentiment composition in phrases formed by at least one positive and at least one negative word- phrases like happy accident and best winter break, and (2) exploring sentiment composition in phrases formed with negators, modals, and degree adverbs.
Systems and Code
- The NRC-Canada sentiment anaysis system.
- The AffectiveTweets Package: Felipe Bravo-Marquez implemented the AffectiveTweets for the Weka machine learning workbench that provides a collection of filters for extracting state-of-the-art features from tweets for sentiment classification/regression and other related tasks. The package is especially useful to generate feature vectors from a large number of affect lexicons. The vector can then be concatenated to other features vectors (say dense-distributed representations of the text) to improve perfomance.
- Code to assist with best-worst-scaling annotations. It includes a script to produce 4-tuples with desired term distributions, a script to produce real-valued scores from best-worst annotations, as well as a script to calculate split-half reliability of the annotations.
- Sentiment Analysis of Social
Media Texts. Saif M. Mohammad and Xiaodan Zhu. Tutorial at the
2014 Conference on Empirical Methods on Natural Language Processing, October
2014, Doha, Qatar.
Presentation Video Proposal
- A Practical Guide to Sentiment Annotation: Challenges and Solutions. Saif M. Mohammad, In Proceedings of the NAACL 2016 Workshop on Computational Approaches to Subjectivity, Sentiment, and Social Media (WASSA), June 2014, San Diego, California.
Paper (pdf) BibTeX Presentation
- Sentiment Analysis: Detecting Valence, Emotions, and Other Affectual States from Text. Saif M. Mohammad, Emotion Measurement, 2016.
Pre-print version BibTeX
(This is a survey on automatic methods for affect analysis.)