I am looking for scholarly, peer-reviewed articles that discuss natural language processing (NLP) involving chat or text messaging lingo/acronyms and the affect of chat participants based on language and emoticons. Anyone have a good recommendation?

I am already familiar with the recent work involving using Twitter to assess the general mood of society as a means of predicting the stock market. They used the Google-Profile of Mood States (GPOMS) that measures mood as Calm, Alert, Sure, Vital, Kind, or Happy. I am looking for other examples that assess general affect, ideally by applying more scientific psychometric tests to NLP.

I am not trying to use the data for prediction. I am seeking to use machine learning algorithms to classify/categorize conversations.


Bollen, J., Mao, H., Zeng, X-J. (2011). Twitter mood predicts the stock market. Journal of Computational Science, 2(1),1-8. [DOI]


2 Answers 2


The field that is doing this work you describe is sentiment analysis. From Wikipedia:

A basic task in sentiment analysis is classifying the polarity of a given text at the document, sentence, or feature/aspect level — whether the expressed opinion in a document, a sentence or an entity feature/aspect is positive, negative, or neutral. Advanced, "beyond polarity" sentiment classification looks, for instance, at emotional states such as "angry," "sad," and "happy."

From an introductory course (lots of good references on this page)

This work is in the general area of sentiment analysis, opinion extraction or opinion mining, and feature-based opinion summarization from the user-generated content or user-generated media on the Web, e.g., reviews, forum and group discussions, and blogs. In our KDD-2004 (Minqing Hu and Bing Liu. "Mining and summarizing customer reviews." Proceedings of the ACM SIGKDD International Conference on Knowledge Discovery & Data Mining, Seattle, Washington, USA, Aug 22-25, 2004.) paper, we proposed the Feature-Based Opinion Mining model, which is now also called Aspect-Based Opinion Mining (as the term feature here can confuse with the term feature used in machine learning). The output of such opinion mining is a feature-based opinion summary or aspect-based opinion summary. The area is also related to sentiment classification. Our current work is in two main areas, which reflect two kinds of opinions (or evaluations)

  • Mining regular (or direct) opinions. Ex: (1). This camera is great. (2). After taking the drug, I got stomach pain.
  • Mining comparative opinions. Ex: Coke tastes better than Pepsi.

In terms of your actual goals, scroll down to extra credit on this page, and you'll find an exercise that goes through a scenario close to what you describe with emoticons.

In terms of peer-reviewed, Chmiel A, Sienkiewicz J, et al (2011). Collective emotions online and their influence on community life, PLoS One, 6(7), e22207. PDF. I'm sure there are others in mainstream NLP journals, but I'm for want of a database that lists them.


I would search under the topic of affective computing especially in detecting and recognizing emotional information and then specialize on NLP methods in this area.

Here are a few articles of interest:

Visualizing the affective structure of a text document

A model of textual affect sensing using real-world knowledge

Saurus: an emotionally-weighted thesaurus


Gouldstone, J., Liu, H., Lieberman, H., Ishii, H. (2006). Saurus: an emotionally-weighted thesaurus. Computational aesthetics: Artificial intelligence approaches to beauty and happiness, Technical Report WS-06-04.

Liu, H., Selker, T., Lieberman, H. (2003). Visualizing the Affective Structure of a Text Document. Proceedings of the Conference on Human Factors in Computing Systems, CHI 2003, April 5-10, 2003, Ft. Lauderdale, FL, USA. ACM 2003, ISBN 1-58113-637-4, pp. 740-741.

Liu, H., Lieberman, H., Selker, T. (2003). A Model of Textual Affect Sensing using Real-World Knowledge. Proceedings of the 2003 International Conference on Intelligent User Interfaces, IUI 2003, January 12-15, 2003, Miami, FL, USA. ACM 2003, ISBN 1-58113-586-6, pp. 125-132. Miami, Florida.


Your Answer

By clicking “Post Your Answer”, you agree to our terms of service and acknowledge you have read our privacy policy.

Not the answer you're looking for? Browse other questions tagged or ask your own question.