From Brede Wiki

Jump to: navigation, search
Dataset (help)
Category: AFINN

Sentiment analysis

Papers: DOAJ Google Scholar PubMed
Ontologies: MeSH NeuroLex Wikidata Wikipedia
Other: Google Twitter WolframAlpha

AFINN is an affective lexicon by Finn Årup Nielsen. Previous and present versions of the word list are available in a zip file:

The word lists are also distributed from within a Python program:

This Python package also contains a Danish word list.

The word list and its evaluation are described in:

A new ANEW: evaluation of a word list for sentiment analysis in microblogs


[edit] Relationship to ANEW

Although the title of the associated paper suggests that it is based on the ANEW labeled corpus, it is not. The title is simply a wordpun. It was developed independently of the wordlist, and it is not a revision of it. Compared to ANEW, the AFINN word list has more words and includes obscene words. ANEW on the other hand has (besides valence) arousal and dominance for each word and each word has been labeled by several persons and the mean and standard deviation are given. The AFINN was only labeled by Finn Årup Nielsen. Finn Årup Nielsen was in no way involved in development of ANEW. ANEW was developed by Margaret M. Bradley and Peter J. Lang.

The word list has been used for sentiment analysis and is developed in the Responsible Business in the Blogosphere project.

[edit] Evaluation

  1. Correlation with Alan Mislove's 1000 AMT-labeled tweet post, see A new ANEW: evaluation of a word list for sentiment analysis in microblogs
  2. Correlation with 50 positive and negative manually labeled tweets: 76%-78%, see Analyzing emotion on Twitter for using modeling
  1. Around 0.55 in three-class accuracy on RepLab Twitter data set. However, this is a combined list consisting of AFINN, SentiWordNet and Liu wordlist used as features in a decision tree machine learning classifier.[1]
  2. 0.72-0.77 accuracy in two-class polarity classification with Twitter corpora.[2]
  3. 0.65-0.79 accuracy in two-class subjectivity classification with Twitter corpora.[3]
  4. Performance on product reviews is reported in Data-driven integration of multiple sentiment dictionaries for lexicon-based sentiment classification of product reviews.
  5. 71% and 63% accuracy on two-class polarity classification on Twitter data.[4]
  6. 62.2% accuracy on two-class sentiment analysis of the movie review data set
  7. A comparative study on Twitter sentiment analysis: which features are good? 4 different datasets with AFINN as features in a machine learning classifier: 74-75.2% (SemEval dataset), around 70% (Sanders dataset), 58.7-60.5% (Health Care Reform dataset[5]) and around 62.5-62.8% (Obama-McCain Debate dataset[6]). In this study AFINN was shown to be one of the best features for Twitter sentiment analysis.
  8. How translation alters sentiment, part of an Arabic sentiment analysis system.
  9. Evaluating the effectiveness of hashtags as predictors of the sentiment of tweets shows accuracy results for classifying between sentiment and non-sentiment tweets.

See also AFINN used with Italian translation in IRADABE: adapting english lexicons to the Italian sentiment polarity classification task.

[edit] See also

[edit] Papers

  1. A new ANEW: evaluation of a word list for sentiment analysis in microblogs. Evaluation of the word list with 2477 words.

[edit] Applications of the word list

  1. 2012 presidential elections on Twitter - an analysis of how the US and French election were reflected in tweets
  2. A clustering analysis of tweet length and its relation to sentiment
  3. A comparative study on Twitter sentiment analysis: which features are good?
  4. A constrained multi-view clustering approach to influence role detection
  5. A data-centric framework for development and deployment of Internet of Things applications in clouds
  6. A design proto- pattern for continuously evaluated forecasting in IBM® InfoSphere® Streams
  7. A framework for knowledge derivation incorporating trust and quality of data (2013)
  8. A fine-grained sentiment analysis approach for detecting crisis related microposts (2013)
  9. A hybrid approach for emotion detection in support of affective interaction
  10. A longitudinal study of follow predictors on Twitter (2013)
  11. A novel transit rider satisfaction metric: rider sentiments measured from online social media data
  12. A rule-based approach to implicit emotion detection in text (2015)
  13. A simple and efficient algorithm for lexicon generation inspired by structural balance theory
  14. Aesthetic considerations for automated platformer design (2012)
  15. Analyzing and predicting news popularity on Twitter (2015)
  16. Aspect based sentiment analysis (2014, PhD Thesis)
  17. Audience targeting by B-to-B advertisement classification: a neural network approach
  18. AUEB: two stage sentiment analysis of social network messages (2014, SemEval)
  19. Bias-aware lexicon-based sentiment analysis
  20. Bimodal feature-based fusion for real-time emotion recognition in a mobile context
  21. BiSAL - a bilingual sentiment analysis lexicon to analyze Dark Web forums for cyber security
  22. BOUNCE: sentiment classification in Twitter using rich feature sets (2013)
  23. Building domain specific sentiment lexicons combining information from many sentiment lexicons and a domain specific corpus
  24. Building sentiment lexicons applying graph theory on information from three Norwegian thesauruses
  25. Can Twitter_Trends predict election results? Evidence from 2014 Indian general election
  26. Capturing place semantics from users' interaction on the geosocial web (2014)
  27. Catching fish in the stream: real time analysis of audience behavior in social media (2013)
  28. Character-to-character sentiment analysis in Shakespeare's plays (2013)
  29. CLaC-SentiPipe: SemEval2015 Subtasks 10 B,E, and Task 11
  30. Citius: a naive-Bayes strategy for sentiment analysis on English tweets (2014)
  31. Combining strengths, emotions and polarities for boosting Twitter sentiment analysis
  32. Combining textual pre-game reports and statistical data for predicting success in the National Hockey League (2014)
  33. Constructing sentiment lexicons in Norwegian from a large text corpus
  34. Contextual sentiment analysis using conditional random fields
  35. Contradiction detection between opinions (2013)
  36. Cooperative, dynamic Twitter parsing and visualization for dark network analysis (2013)
  37. Crawling JavaScript websites using WebKit – with application to analysis of hate speech in online discussions (2013)
  38. Crowd sentiment detection during disasters and crises
  39. Cues to deception in social media communications
  40. Data-driven integration of multiple sentiment dictionaries for lexicon-based sentiment classification of product reviews
  41. Detecting predatory behaviour in game chats (2015)
  42. DigitalHealth: exploring users' perspectives through social media analysis (2015)
  43. dispel4py: an agile framework for data-intensive eScience
  44. Discovering content-based behavioral roles in social networks
  45. Empirical study of relationship between Twitter mood and stock market from an Indian context (2015)
  46. Enhanced news-reading: interactive and visual integration of social media information
  47. Enhancing lexicon-based review classification by merging and revising sentiment dictionaries
  48. Ensemble learning methods for pay-per-click campaign management (2015)
  49. Ensemble learning techniques for structured and unstructured data (2015, thesis)
  50. Evaluating the effectiveness of hashtags as predictors of the sentiment of tweets
  51. Exploratory search on Twitter utilizing user feedback and multi-perspective microblog analysis
  52. Extracting sentiment networks from Shakespeare's plays
  53. FBM-Yahoo! at RepLab 2012 (2012)
  54. Forex-Foreteller: currency trend modeling using news articles
  55. From unlabelled tweets to Twitter-specific opinion words
  56. Full-FACE poetry generation
  57. Fuzzy subjective sentiment phrases: a context sensitive and self-maintaining sentiment lexicon (2014)
  58. Geo-spatial event detection in the Twitter stream
  59. GeoSRS: a hybrid social recommender system for geolocated data (2015)
  60. Good friends, bad news - affect and virality in Twitter (2011)
  61. GTI: an unsupervised approach for sentiment analysis in Twitter
  62. Identifying consumers' arguments in text (2012)
  63. Identifying disputed topics in the news (2014)
  64. IIIT-H at SemEval 2015: Twitter sentiment analysis - the good, the bad and the neutral!
  65. In search of reputation assessment: experiences with polarity classification in RepLab 2013 (2013)
  66. Inferring topic-dependent influence roles of Twitter users
  67. IOA: improving SVM based sentiment classification through post processing
  68. IRADABE: adapting english lexicons to the Italian sentiment polarity classification task
  69. KLUE: simple and robust methods for polarity classification
  70. KLUEless: polarity classification and association
  71. Learning to recognize affective polarity in similes
  72. language-related information for the Linguistic Linked Data Cloud
  73. LLT-PolyU: identifying sentiment intensity in ironic tweets
  74. Machine reading for abstractive summarization of customer reviews in the touristic domain
  75. Making the most of tweet-inherent features for social spam detection on Twitter
  76. Measuring the influence of mass media on opinion segregation through Twitter (2014)
  77. Measuring NBA players mood by mining athlete-generated content (2015)
  78. Meta-level sentiment models for big social data analysis
  79. Mining Facebook data for predictive personality modeling
  80. Monitoring travel-related information on social media through sentiment analysis (2014)
  81. Movie script summarization as graph-based scene extraction
  82. Multi-domain collaboration for Web-based literature browsing and curation
  83. Networks and language in the 2010 election
  84. New lessions from the War in Bosnia
  85. NTNU: domain semi-independent short message sentiment classification
  86. On enhancing the label propagation algorithm for sentiment analysis using active learning with an artificial oracle
  87. Positive, negative, or neutral: learning an expanded opinion lexicon from emoticon-annotated tweets
  88. Predictingg tie strength with the Facebook API (2014)
  89. Privacy nudges for social media: an exploratory Facebook study (2013)
  90. Probing of geospatial stream data to report disorientation (2013)
  91. Real-time monitoring of sentiment in business related Wikipedia (2013)
  92. Rule-based visual mappings -- with a case study on poetry visualization (2013)
  93. Representing and resolving negation for sentiment analysis (2012)
  94. Restaurant rating: industrial standard and word-of-mouth a text mining and multi-dimensional sentiment analysis
  95. Sarcasm as contrast between a positive sentiment and negative situation (2013)
  96. Semi-automated argumentative analysis of online product reviews (2012)
  97. Sensing social media for corporate reputation management: a business agility perspective
  98. Sentiment analysis on microblogs for natural disasters management: a study on the 2014 Genoa Floodings
  99. Sentiment classification of online political discussions: a comparison of a word-based and dependency-based method (2014)
  100. Sentiue: target and aspect based sentiment analysis in SemEval-2015 Task 12 (2015)
  101. Simple approaches of sentiment analysis via ensemble learning
  102. Solving the online review puzzle
  103. Some remarks on the internal consistency of online consumer reviews (2013)
  104. Someone to talk to in Advances in affective and pleasurable design.
  105. Strategies of legitimacy through social media: the networked strategy (2015)
  106. Study of different algorithms in sentiment analysis and the existing issues
  107. Suicidal tendencies: the automatic classification of suicidal and non-suicidal lyricists using NLP (2013)
  108. Summarization of yes/no questions using a feature function model (2011)
  109. Text normalization of code mix and sentiment analysis
  110. The emergence of online community leadership
  111. The FloWr framework: automated flowchart construction, optimisation and alteration for creative systems (2014)
  112. The impact of affective verbal content on predicting personality impressions in YouTube videos
  113. The lexicon-based sentiment analysis for fan page ranking in Facebook (2014)
  114. The painful tweet: text, sentiment, and community structure analyses of tweets pertaining to pain (2015)
  115. The power of Twitter on predicting box office revenues (2012)
  116. The QWERTY effect: how typing shapes the meanings of words (2012)
  117. The use of POS sequence for analyzing sentence pattern in Twitter sentiment analysis
  118. Twista - an application for the analysis and visualization of tailored tweet collections
  119. TwitterHawk: a feature bucket approach to sentiment analysis (2015)
  120. Towards automated personality identification using speech acts
  121. Topic and sentiment analysis on OSNs: a case study of advertising strategies on Twitter
  122. Trusting smartphone apps? To install or not to install, that is the question (2013)
  123. Tuned models of peer assessment in MOOCs (2013)
  124. Tweeting the meeting: an in-depth analysis of Twitter activity at Kidney Week 2011 (2012)
  125. Tweets are forever: a large-scale quantitative analysis of deleted tweets (2013)
  126. Twitter for public health: an open-source data solution
  127. Twitter sentiment analysis on E-commerce websites in India
  128. Twitter sentiment classification on Sanders data using hybrid approach
  129. Twitter sentiment detection via ensemble classification using averaged confidence scores
  130. Two classifiers in arbiter tree to analyze data
  131. US presidential election 2012 prediction using census corrected Twitter model (2012)
  132. Use of social media data to explore crisis informatics(?) (2015)
  133. Using combined lexical resources to identify hashtag types
  134. Using hashtags as labels for supervised learning of emotions in Twitter messages (2014)
  135. Using social media data to study people's perception and knowledge of environments
  136. Valence shifting: is it a valid task?
  137. ValenTo: sentiment analysis of figurative language tweets with irony and sarcasm
  138. Voices of victory: a computational focus group framework for tracking opinion shift in real time
  139. Webis: an ensemble for Twitter sentiment detection
  140. Whisper: tracing the spatiotemporal process of information diffusion in real time (2012)

[edit] Mentioning

  1. A machine learning attack against the civil rights CAPTCHA
  2. A mathematical approach to gauging influence by identifying shifts in the emotions of social media users
  3. A novel sentiment analysis of social networks using supervised learning
  4. A quantitative analysis of gender differences in movies using psycholinguistic normatives
  5. A survey on opinion mining and sentiment analysis: tasks, approaches and applications
  6. Adapting sentiment lexicons using contextual semantics for sentiment analysis of Twitter
  7. Advanced classification lists (dirty word lists) for automatic security classification
  8. An integrated text analytic framework for product defect discovery (2014)
  9. Automatic mood classification of Indonesian tweets using linguistic approach
  10. Classifying emotion in Thai youtube comments
  11. Crawling JavaScript websites using WebKit - with application to analysis of hate speech in online discussions
  12. Comparative study: the implementation of machine learning method for sentiment analysis in social media. A recommendation for future research
  13. Demystifying MapReduce
  14. Detection and scoring of Internet slangs for sentiment analysis using SentiWordNet
  15. Differential emotions and the stock market - the case of company-specific trading
  16. Engagement with health agencies on Twitter
  17. Feature-level sentiment analysis applied to Brazilian Portuguese reviews
  18. Feature sentiment diversification of user generated reviews: the FREuD approach (2015)
  19. GU-MLT-LT: Sentiment Analysis of Short Messages using Linguistic Features and Stochastic Gradient Descent
  20. Increasing the willingness to collaborate online: an analysis of sentiment-driven interactions in peer content production (2011, closed access)
  21. NTNU: domain semi-independent short message sentiment classification
  22. Methodology for Twitter sentiment analysis
  23. Mining fine-grained argument elements
  24. Mining social network data for cyber physical system
  25. Opinion recognition on movie reviews by combining classifiers
  26. OpinionMining-ML
  27. Overview of the Evalita 2014 SENTIment POLarity Classification task
  28. Predicting personality traits of Chinese users based on Facebook wall posts (2015)
  29. Privacy nudges for OSNs: a review (2014)
  30. Reducing sparsity in sentiment analysis data using novel dimensionality reduction approaches
  31. Retrieving minority product reviews using positive/negative skewness
  32. SemEval-2013 task 2: sentiment analysis in Twitter
  33. SemEval-2015 task 12: aspect based sentiment analysis
  34. Sentiment analysis over social networks: an overview
  35. Sentiment analysis: detecting valence, emotions, and other affectual states from text (Saif M. Mohammad review)
  36. Sentiment analysis techniques in recent works
  37. SentiMeter-Br: Facebook and Twitter analysis tool to discover consumers' sentiment
  38. Social data integration and analytics for health intelligence
  39. State of the art language technologies for Italian: the EVALITA 2014 perspective
  40. Text mining of news-headlines for FOREX market prediction: a multi-layer dimension reduction algorithm with semantics and sentiment
  41. The challenges of sentiment detection in the social programmer ecosystem
  42. The muses of poetry - in search of the poetic experience
  43. The sound of valence: phonological features predict word meaning
  44. Time-space varying visual analysis of micro-blog sentiment
  45. The next generation poetic experience
  46. The potential of microblogs for the study of public perceptions of climate change
  47. VADER: a parsimonious rule-based model for sentiment analysis of social media text
  48. Workshop on computational personality recognition: shared task

[edit] Student papers

  1. Análisis Estático y Dinámico de opiniones en Twitter (Felipe José Bravo Márquez, 2013)
  2. Analyzing emotion on Twitter for user modeling (Shaolong Li, Master Thesis, 2013)
  3. Aspect-based opinion summarization of product reviews on social media (Ásgeir Ögmundarson, Master Thesis, 2015)
  4. Classification and visualisation of Twitter sentiment data (mentioning, Mikael Brevik, Øyvind Selmer, 2013 Master Thesis)
  5. Combining lexicon- and learning-based approaches for improved performance and convenience in sentiment classification
  6. Distributional methods for sentiment analysis (Emmanuele Chersoni, 2013, Master Thesis)
  7. Evaluation of natural language processing techniques for sentiment analysis on tweets (2012, Bachelor Thesis)
  8. Exploitation of tweets to measure experienced utility (Allison Madigan, 2013)
  9. Forecasting success in the National Hockey League using in-game statistics and textual data (Master Thesis, 2014)
  10. Natural language processing methods for attitudinal near-synonymy
  11. Opinion mining and name entity detection from news comments
  12. Real-time Twitter sentiment classification based on Apache Storm (2015, Master Thesis)
  13. Relationships between social media sentiment, customer satisfaction, and stock price performance (Master Thesis, 2013)
  14. Retweets--but not just retweets: quantifying and predicting influence on Twitter (2012, Bachelor thesis)
  15. Sentiment mining using machine learning optimization (2015 Master Thesis)
  16. Social media sentiment analysis (2014 Master Thesis)
  17. Social media sentiment analysis for stock price behavior prediction
  18. Using movie screenplays as a barometer for mood in history (2014, [1])
  19. Twitter data analysis for financial markets
  20. TwitterCritic: sentiment analysis of tweets to predict TV ratings
  21. Using social media content to inform agent-based models for humanitarian crisis response (Bachelor Thesis, 2014)
  22. Why not! Sequence labeling the scope of negation using dependency features (2012 Master Thesis)
  23. Sentiment analysis of microblogs (Tobias Günther, 2013)

Andrew Ng's CS 229 class:

  1. Robert Chang, Sam Pimentel, Alexandr Svistunov, Sentiment Analysis of Occupy Wall Street Tweets, 2011. [2]
  2. Derek Farren, Predicting retail website anomalies using Twitter data, 2012. [3]

[edit] Mentioning

  1. A framework to analyse and visualise public sentiment using Twitter data
  2. Inference of personality using social media profiles
  3. Mining social media: methods and approaches for content analysis
  4. Sentiment analysis for Bangla microblog posts
  5. Sentiment analysis of Norwegian Twitter messages
  6. Sentiment mining using machine learning optimization

[edit] Blogs

  1. Finn Årup Nielsen's blog, posts tagged with 'afinn'.
  2. Tracking US Sentiments Over Time In Wikileaks
  3. Kaushal Agrawal – Data Visualization – Mood of the Artist
  4. First shot: Sentiment Analysis in R, Andy Bromberg
  5. All Your Tweets Are Belong To Us: the Twitterverse declares a winner
  6. The Happiest And Saddest Fans In Baseball, FiveThirtyEight, 2015.

[edit] Mentioning

  1. Sometimes I think we don’t deserve good data Google Ngram.
  2. Introduction to Sentiment Analysis , Carl Anderson,

[edit] Tools

  1. Simplest sentiment analysis in Python with AFINN (note UNICODE issue for the word naïve, use "unicode(w, 'utf-8')" )
  2. Javascript
    1. AFINN-based sentiment analysis for Node.js
    2. application
    3. Retext sentiment
  3. lexicons, Python and Javascript libraries
  4. AFINN-based sentiment analysis in Perl
  5. Afinn-for-Norsk
  6. Django
  7. Common Lisp
  8. troll, Javascript, Andrew Sliwinski.
  9. C-sharp (C#) by Tomasz Cielecki
  10. Große Gefühle Heise c't magazine in German with source code and tools in Ruby and Java.
  11. SAS Text Mining ("what's new" for the commercial product)
  12. A Better Place, chrome extension. The extension was made in response to Experimental evidence of massive-scale emotional contagion through social networks.
  13. syuzhet, R. [4]
  14. Data Science Toolkit, webservice that uses AFINN for online sentiment analysis

[edit] Language versions

[edit] Services

[edit] Coursera

Bill Howe's Coursera course Introduction to Data Science has a sentiment analysis task were - apparently - AFINN is used on Twitter posts

[edit] References

  1. In search of reputation assessment: experiences with polarity classification in RepLab 2013
  2. Meta-level sentiment models for big social data analysis
  3. Meta-level sentiment models for big social data analysis
  4. Fuzzy subjective sentiment phrases: a context sensitive and self-maintaining sentiment lexicon
  5. Twitter polarity classification with label propagation over lexical links and the follower graph
  6. Twitter polarity classification with label propagation over lexical links and the follower graph
Personal tools