Traditionally in NLP, sentiment analysis aims to identify the opinion or sentiment of the speaker (writer) toward a certain topic. The increasing availability of massive written tidbits of people everyday life enables the large-scale measurement of people’s mood. Peter Sheridan Dodds and Christopher M suggested a very simple way to measure happiness from written texts[^1]. This method was used in Twittermood and several other researches[^2]. Facebook is also doing similar measurements[^3][^4]. Positive/negative dichotomy is probably too simplistic[^5].
Regarding Homophily and influence, it was shown that the assortativity of happiness can be measured in online social networks[^6][^7].
Interesting application: food mood: http://www.aaai.org/ocs/index.php/ICWSM/ICWSM12/paper/viewFile/4776/5100
How does sentiment analysis differentiate different domains[^8]?
- CACM: Techniques and Applications for Sentiment Analysis
- Benchmarking sentiment analysis methods for large-scale texts: A case for using continuum-scored words and word shift graphs
- SentiBench - a benchmark comparison of state-of-the-practice sentiment analysis methods
Using word2vec or doc2vec
- http://www.cl.cam.ac.uk/research/srg/netos/emotionsense/ - using mobile phones.
- Deeply Moving: Deep Learning for Sentiment Analysis
- https://storify.com/clancynewyork/contretemps-a-syuzhet - Syuzhet. Are there Archetypes of stories? - see Shapes of Stories
Softwares and data
- Temporal Patterns of Happiness and Information in a Global Social Network: Hedonometrics and Twitter - an expansion of ANEW.
- Stanford: CS224N - Final Project Report - Twitter sentiment analysis
- 10 Reasons Why Automated Social Media Listening Tools Fail
- Collective emotions online and their influence on community life
- Thumbs up? Sentiment Classification using Machine Learning Techniques
- Affective News: The Automated Coding of Sentiment in Political Texts
- Emotional persistence in online chatting communities
- Characterizing Happy Communities using Tweets
- Baselines and Bigrams: Simple, Good Sentiment and Topic Classification
- Coupling news sentiment with web browsing data predicts intra-day stock prices
↑ Peter Sheridan Dodds and Christopher M. Danforth (2010). “Measuring the Happiness of Large-Scale Written Expression: Songs, Blogs, and Presidents”. J. Happiness Stud. 11: 441-456. doi:10.1007/s10902-009-9150-9. http://www.springerlink.com/content/757723154j4w726k/.
↑ Peter Sheridan Dodds et al. (2011). Temporal patterns of happiness and information in a global social network: Hedonometrics and Twitter. http://arxiv.org/abs/1101.5120.
↑ “Gross National Happiness”. http://apps.facebook.com/usa_gnh/. Retrieved February 4, 2011.
↑ Adam D. I. Kramer (March 23, 2010). “How Happy Are We?”. http://www.facebook.com/blog.php?post=150162112130. Retrieved February 4, 2011.
↑ “Not All Moods are Created Equal! Exploring Human Emotional States in Social Media”. http://research.microsoft.com/en-us/um/people/munmund/pubs/icwsm_12_1.pdf.
↑ “Crossing Media Streams with Sentiment: Domain Adaptation in Blogs, Reviews and Twitter”. http://www.aaai.org/ocs/index.php/ICWSM/ICWSM12/paper/viewFile/4580/4988.