SentiStrength: Sentiment Strength Detection in MySpace and Twitter Mike Thelwall Statistical Cybermetrics Research Group University of Wolverhampton, UK.

Slides:



Advertisements
Similar presentations
Detecting and analysing emotion in social network sites Mike Thelwall Statistical Cybermetrics Research Group University of Wolverhampton, UK Virtual Knowledge.
Advertisements

On the application of GP for software engineering predictive modeling: A systematic review Expert systems with Applications, Vol. 38 no. 9, 2011 Wasif.
Sentiment Analysis on Twitter Data
Imbalanced data David Kauchak CS 451 – Fall 2013.
CPSC 502, Lecture 15Slide 1 Introduction to Artificial Intelligence (AI) Computer Science cpsc502, Lecture 15 Nov, 1, 2011 Slide credit: C. Conati, S.
Large-Scale Entity-Based Online Social Network Profile Linkage.
Supervised Learning Techniques over Twitter Data Kleisarchaki Sofia.
Computational Models of Discourse Analysis Carolyn Penstein Rosé Language Technologies Institute/ Human-Computer Interaction Institute.
Machine Learning in Practice Lecture 7 Carolyn Penstein Rosé Language Technologies Institute/ Human-Computer Interaction Institute.
Pollyanna Gonçalves (UFMG, Brazil) Matheus Araújo (UFMG, Brazil) Fabrício Benevenuto (UFMG, Brazil) Meeyoung Cha (KAIST, Korea) Comparing and Combining.
Time series Word frequencies Sentiment analysis Twitter Analysis for the Social Sciences and Humanities.
A Survey on Text Categorization with Machine Learning Chikayama lab. Dai Saito.
Sentiment Analysis Applied Advertising & Public Relations Research JOMC 279.
Deep Belief Networks for Spam Filtering
ML ALGORITHMS. Algorithm Types Classification (supervised) Given -> A set of classified examples “instances” Produce -> A way of classifying new examples.
Evaluation of Results (classifiers, and beyond) Biplav Srivastava Sources: [Witten&Frank00] Witten, I.H. and Frank, E. Data Mining - Practical Machine.
Classifiers, Part 3 Week 1, Video 5 Classification  There is something you want to predict (“the label”)  The thing you want to predict is categorical.
Slide Image Retrieval: A Preliminary Study Guo Min Liew and Min-Yen Kan National University of Singapore Web IR / NLP Group (WING)
Artificial Intelligence Lecture No. 28 Dr. Asad Ali Safi ​ Assistant Professor, Department of Computer Science, COMSATS Institute of Information Technology.
Processing of large document collections Part 2 (Text categorization) Helena Ahonen-Myka Spring 2006.
1 / 12 PSLC Summer School, June 21, 2007 Identifying Students’ Gradual Understanding of Physics Concepts Using TagHelper Tools Nava L.
Using Transactional Information to Predict Link Strength in Online Social Networks Indika Kahanda and Jennifer Neville Purdue University.
8/25/05 Cognitive Computations Software Tutorial Page 1 SNoW: Sparse Network of Winnows Presented by Nick Rizzolo.
Document Categorization Problem: given –a collection of documents, and –a taxonomy of subject areas Classification: Determine the subject area(s) most.
From Machine Learning to Deep Learning. Topics that I will Cover (subject to some minor adjustment) Week 2: Introduction to Deep Learning Week 3: Logistic.
Combining multiple learners Usman Roshan. Bagging Randomly sample training data Determine classifier C i on sampled data Goto step 1 and repeat m times.
Today Ensemble Methods. Recap of the course. Classifier Fusion
Exploiting Context Analysis for Combining Multiple Entity Resolution Systems -Ramu Bandaru Zhaoqi Chen Dmitri V.kalashnikov Sharad Mehrotra.
School of Engineering and Computer Science Victoria University of Wellington Copyright: Peter Andreae, VUW Image Recognition COMP # 18.
TEXT ANALYTICS - LABS Maha Althobaiti Udo Kruschwitz Massimo Poesio.
Learning with AdaBoost
​ Text Analytics ​ Teradata & Sabanci University ​ April, 2015.
Slides for “Data Mining” by I. H. Witten and E. Frank.
Classification (slides adapted from Rob Schapire) Eran Segal Weizmann Institute.
Creating Subjective and Objective Sentence Classifier from Unannotated Texts Janyce Wiebe and Ellen Riloff Department of Computer Science University of.
CSC 594 Topics in AI – Text Mining and Analytics
Recognizing Stances in Online Debates Unsupervised opinion analysis method for debate-side classification. Mine the web to learn associations that are.
Exploring in the Weblog Space by Detecting Informative and Affective Articles Xiaochuan Ni, Gui-Rong Xue, Xiao Ling, Yong Yu Shanghai Jiao-Tong University.
Classification Ensemble Methods 1
From Words to Senses: A Case Study of Subjectivity Recognition Author: Fangzhong Su & Katja Markert (University of Leeds, UK) Source: COLING 2008 Reporter:
NTU & MSRA Ming-Feng Tsai
Notes on HW 1 grading I gave full credit as long as you gave a description, confusion matrix, and working code Many people’s descriptions were quite short.
Combining multiple learners Usman Roshan. Decision tree From Alpaydin, 2010.
Learning Event Durations from Event Descriptions Feng Pan, Rutu Mulkar, Jerry R. Hobbs University of Southern California ACL ’ 06.
Machine Learning in Practice Lecture 8 Carolyn Penstein Rosé Language Technologies Institute/ Human-Computer Interaction Institute.
2014 Lexicon-Based Sentiment Analysis Using the Most-Mentioned Word Tree Oct 10 th, 2014 Bo-Hyun Kim, Sr. Software Engineer With Lina Chen, Sr. Software.
Twitter as a Corpus for Sentiment Analysis and Opinion Mining
Multi-Class Sentiment Analysis with Clustering and Score Representation Yan Zhu.
Machine Learning Artificial Neural Networks MPλ ∀ Stergiou Theodoros 1.
Data Mining: Concepts and Techniques1 Prediction Prediction vs. classification Classification predicts categorical class label Prediction predicts continuous-valued.
A Sentiment-Based Approach to Twitter User Recommendation BY AJAY ABDULPUR RAJARAM NIKKAM.
A Simple Approach for Author Profiling in MapReduce
Experience Report: System Log Analysis for Anomaly Detection
Data Mining, Machine Learning, Data Analysis, etc. scikit-learn
Sentiment Analysis: The Emotionality of Discourse .
An Empirical Comparison of Supervised Learning Algorithms
MIRA, SVM, k-NN Lirong Xia. MIRA, SVM, k-NN Lirong Xia.
Sentiment analysis tools
Rosta Farzan and Keyang Zheng, School of Computing and Information
Describe two features of…
network of simple neuron-like computing elements
iSRD Spam Review Detection with Imbalanced Data Distributions
Machine Learning in Practice Lecture 7
Data Mining, Machine Learning, Data Analysis, etc. scikit-learn
Somi Jacob and Christian Bach
Data Mining, Machine Learning, Data Analysis, etc. scikit-learn
Introduction to Sentiment Analysis
Chapter 10 Content Analysis
MIRA, SVM, k-NN Lirong Xia. MIRA, SVM, k-NN Lirong Xia.
Austin Karingada, Jacob Handy, Adviser : Dr
Presentation transcript:

SentiStrength: Sentiment Strength Detection in MySpace and Twitter Mike Thelwall Statistical Cybermetrics Research Group University of Wolverhampton, UK Virtual Knowledge Studio (VKS) Information Studies

SentiStrength Objective 1. Detect positive and negative sentiment strength in short informal text 1. Develop workarounds for lack of standard grammar and spelling 2. Harness emotion expression forms unique to MySpace or CMC (e.g., :-) or haaappppyyy!!!) 3. Classify simultaneously as positive 1-5 AND negative 1-5 sentiment 2. Apply to MySpace comments and social issues

SentiStrength Algorithm - Core List of 890 positive and negative sentiment terms and strengths (1 to 5), e.g. ache = -2, dislike = -3, hate=-4, excruciating -5 encourage = 2, coolest = 3, lover = 4 Sentiment strength is highest in sentence; or highest sentence if multiple sentences

Examples My legs ache. You are the coolest. I hate Paul but encourage him , -2 positive, negative 3, -1 2, -4

Term Strength Optimisation Term strengths (e.g., ache = -2) initially fixed by human coder Term strengths optimised on training set with 10-fold cross-validation Adjust term strengths to give best training set results then evaluate on test set E.g., training set: “My legs ache”: coder sentiment = 1,-3 => adjust sentiment of “ache” from -2 to -3.

SentiStrength Algorithm -Extra Spelling correction for repeated letters Helllllo -> Hello (emphasis: llll) Tagging approach used (see next slide) Extra heuristics Emphasis acts to enhance + or – emotion Emotion words ignored in questions Take strongest positive or negative expression in whole comment Booster words (e.g., very, some)

Tagging HIIIIII MY MATE!!!!!!!! HIIIIII MY MATE !!!!!!!! HI MY MATE! 2 3 Overall 3, -1 mate = 2

Experiments Development data = 2600 MySpace comments coded by 1 coder Test data = 1041 MySpace comments coded by 3 independent coders Comparison against a range of standard machine learning algorithms

Inter-coder agreement Comparison+ve agree- ment -ve agree- ment Coder 1 vs %67.3% Coder 1 vs %76.3% Coder 2 vs %68.2% Krippendorff’s inter-coder weighted alpha = for positive and for negative sentiment Only moderate agreement between coders but it is a hard 5-category task

Machine learning methods +ve

Machine learning methods -ve

Results:+ve sentiment strength AlgorithmOpt. Feat. Accu- racy Acc. +/- 1 class Corr.Mean % abs. error SentiStrength-60.6%96.9% % Simple logistic regression %96.1% % SVM (SMO) %95.4% % J48 classification tree %95.9% % JRip rule-based classifier %96.4% % SVM regression (SMO) %97.3% % AdaBoost %97.5% % Decision table %96.7% % Multilayer Perceptron %94.1% % Naïve Bayes %91.4% % Baseline-47.3%94.0%-31.2% Random-19.8%56.9% %

Results:-ve sentiment strength AlgorithmOpt. feat. AccuracyAcc. +/- 1 class Corr.Mean % absolute error SVM (SMO) %92.7% % SVM regression (SMO) %91.9% % Simple logistic regression %92.2% % SentiStrength-72.8%95.1% % Decision table %92.1% % JRip rule-based classifier %91.5% % J48 classification tree %91.6% % Multilayer Perceptron %92.5% % AdaBoost %90.6%-16.8% Baseline-69.9%90.6%-16.8% Naïve Bayes %89.8% % Random-20.5%46.0% %

SentiStrength Components Type% Consecutive +ve words not used as boosters61.2 Emoticons ignored61.2 Negating words not switch (e.g., not happy)61.0 SentiStrength standard configuration60.9 Booster words ignored (e.g., very)60.7 Automatic spelling correction disabled60.6 Exclamation marks not given a strength of Extra multiple letters not used as boosters60.4 Neutral words with emphasis not counted as +ve60.1 SentiStrength with all the above changes57.5

Example differences/errors THINK 4 THE ADD Computer (1,-1), Human (2,-1) 0MG 0MG 0MG 0MG 0MG 0MG 0MG 0MG!!!!!!!!!!!!!!!!!!!!N33N3R!!!!!!!!!!!!!!!! Computer (2,-1), Human (5,-1)

Selected variations tested Modification (for positive sentiment) Accuracy +/- 1 class corr.Mean Abs. % err. Negating words not used to switch following sentiment (e.g., not happy) 60.87%97.50% % SentiStrength standard algorithm 60.64%96.90% % Exclamation marks not given a strength of %96.62% % Automatic spelling correction disabled 60.39%96.88% % Extra multiple letters not used as emotion boosters 60.21%96.81% % Neutral words with emphasis not counted as positive emotion 60.13%96.79% % SentiStrength with no extras 57.44%96.07% %

Application - Evidence of emotion homophily in MySpace Automatic analysis of sentiment in 2 million comments exchanged between MySpace friends Correlation of for +ve emotion strength and for –ve People tend to use similar but not identical levels of emotion to their friends in messages

CYBEREMOTIONS = data gathering + complex systems methods + ICT outputs Collective Emotions in Cyberspace Sentistrength

Application – sentiment in Twitter events Analysis of a corpus of 1 month of English Twitter posts Automatic detection of spikes (events) Sentiment strength classification of all posts Assessment of whether sentiment strength increases during important events Result – negative sentiment normally increases, positive sentiment might tend to increase

Automatically-identified Twitter spikes

Chile

Hawaii

#oscars

Tiger Woods

Conclusion Automatic classification of emotion on a 5 point positive and negative scale seems possible for MySpace …And other similar short computer text messages? Hard to get accuracy much over 60%? Next = analyse emotion in online debates

Publication Thelwall, M., Buckley, K., Paltoglou, G. Cai, D., & Kappas, A. (in press). Sentiment strength detection in short informal text. Journal of the American Society for Information Science and Technology.Sentiment strength detection in short informal text Thelwall, M., Wilkinson, D. & Uppal, S.(2010). Data mining emotion in social network communication: Gender differences in MySpace, Journal of the American Society for Information Science and Technology, 61(1), Data mining emotion in social network communication: Gender differences in MySpace