computing feelings: danish approaches to sentiment analysis - daniel hardt

8
Computing Feelings: Danish Approaches to Sentiment Analysis Daniel Hardt Copenhagen Business School 21 February 2014 Daniel Hardt Computing Feelings: Danish Approaches to Sentiment Analy

Upload: cbs-competitiveness-platform

Post on 26-Jan-2015

104 views

Category:

Social Media


0 download

DESCRIPTION

 

TRANSCRIPT

Page 1: Computing Feelings: Danish Approaches to Sentiment Analysis - Daniel Hardt

Computing Feelings: Danish Approaches toSentiment Analysis

Daniel Hardt

Copenhagen Business School

21 February 2014

Daniel Hardt Computing Feelings: Danish Approaches to Sentiment Analysis

Page 2: Computing Feelings: Danish Approaches to Sentiment Analysis - Daniel Hardt

Business

Daniel Hardt Computing Feelings: Danish Approaches to Sentiment Analysis

Page 3: Computing Feelings: Danish Approaches to Sentiment Analysis - Daniel Hardt

Business

Daniel Hardt Computing Feelings: Danish Approaches to Sentiment Analysis

Page 4: Computing Feelings: Danish Approaches to Sentiment Analysis - Daniel Hardt

Business

Daniel Hardt Computing Feelings: Danish Approaches to Sentiment Analysis

Page 5: Computing Feelings: Danish Approaches to Sentiment Analysis - Daniel Hardt

Business

Daniel Hardt Computing Feelings: Danish Approaches to Sentiment Analysis

Page 6: Computing Feelings: Danish Approaches to Sentiment Analysis - Daniel Hardt

Liu, Bing. Sentiment analysis and subjectivity Handbook of natural language processing 2 (2010): 568.

Sentiment analysis or opinion mining is the computationalstudy of opinions, sentiments and emotions expressed intext

Daniel Hardt Computing Feelings: Danish Approaches to Sentiment Analysis

Page 7: Computing Feelings: Danish Approaches to Sentiment Analysis - Daniel Hardt

Machine Learning Methods

Pang, Bo, Lillian Lee, and Shivakumar Vaithyanathan. "Thumbs up?: sentiment classification using machinelearning techniques." Proceedings of the ACL-02 conference on Empirical methods in natural languageprocessing-Volume 10. Association for Computational Linguistics, 2002.

Bag of words: With lexicon of m words, each document d isrepresented by the document vector(n1(d),n2(d), ...,nm(d))Machine Learning: Naive Bayes, Maximum Entropy,Support Vector MachinesNaive Bayes:

Daniel Hardt Computing Feelings: Danish Approaches to Sentiment Analysis

Page 8: Computing Feelings: Danish Approaches to Sentiment Analysis - Daniel Hardt

Deep Learning: Stanford Sentiment Treebank

Socher, Richard, et al. "Recursive deep models for semantic compositionality over a sentiment treebank."

Proceedings of the Conference on Empirical Methods in Natural Language Processing (EMNLP). 2013.

Daniel Hardt Computing Feelings: Danish Approaches to Sentiment Analysis