= Opinion mining, sentiment analysis = [[https://is.muni.cz/auth/predmet/fi/ia161|IA161 Advanced NLP Course]], Course Guarantee: Aleš Horák Prepared by: Zuzana Nevěřilová == State of the Art == Sentiment analysis can be seen as a text categorization task (i.e. is the writer's opinion on a discussed topic X or Y?). It consists of detection of the topic (which can be easy in focused reviews) and detection of the sentiment (which is generally difficult). Opinions are sometimes expressed in a very subtle manner (e.g. the sentence ''How could anyone sit through this movie?'' contains no negative word) [3]. The sentiments are usually simply classified by their polarity (positive, negative) but they can be recognized more in depth (e.g. strongly negative). Recognized opinions are also subject to summarization (e.g. how many people like this new iPhone design?). === References === 1. Bing Liu. Sentiment Analysis and Opinion Mining. Synthesis Lectures on Human Language Technologies. 2012, 5(1): 1-167. DOI: 10.2200/s00416ed1v01y201204hlt016. Draft version available at [[http://www.cs.uic.edu/~liub/FBS/SentimentAnalysis-and-OpinionMining.pdf]] 1. Bing Liu. Sentiment Analysis Tutorial. AAAI-2011, August 8, 2011. Slides available at [[http://www.cs.uic.edu/~liub/FBS/Sentiment-Analysis-tutorial-AAAI-2011.pdf]] 1. Bo Pang, Lillian Lee, and Shivakumar Vaithyanathan, Thumbs up? Sentiment Classification using Machine Learning Techniques, Proceedings of EMNLP 2002. [[http://www.cs.cornell.edu/home/llee/papers/sentiment.pdf]] 1. Liviu P. Dinu and Iulia Iuga. The Naive Bayes classifier in opinion mining: In search of the best feature set. In Alexander Gelbukh, editor, Computational Linguistics and Intelligent Text Processing, volume 7181 of Lecture Notes in Computer Science, pages 556–567. Springer Berlin Heidelberg, 2012. Bing Liu's References: http://www.cs.uic.edu/~liub/FBS/AAAI-2011-tutorial-references.pdf == Practical Session == === Czech Sentiment Analysis === In this workshop, we try several methods for opinion mining. First, we will train a classifier on real Czech data from Seznam.cz (thank you for the data, Seznam.cz guys!). Requirements: python, NLTK module Files: [raw-attachment:reviews.csv:wiki:en/AdvancedNlpCourse reviews.csv],[raw-attachment:reviews_desamb.csv:wiki:en/AdvancedNlpCourse reviews_desamb.csv],[raw-attachment:reviews_czaccent.csv:wiki:en/AdvancedNlpCourse reviews_czaccent.csv],[raw-attachment:reviews_czaccent_desamb.csv:wiki:en/AdvancedNlpCourse reviews_czaccent_desamb.csv],[raw-attachment:classify.py:wiki:en/AdvancedNlpCourse classify.py] `module add python-nltk` in order to make the NLTK module available 1. Create ``, a text file named ia161-UCO-01.txt where UCO is your university ID. 1. Open `reviews.csv`, observe column meanings (Ack. to Karel Votruba, Karel.Votruba@firma.seznam.cz): 1. shop ID 1. positive comment 1. negative comment 1. price/delivery rating 1. communication rating 1. goods/content rating 1. package/return rating 1. complaints procedure rating 1. Run classify.py. 1. What the most informative features? Do they make sense? Write most informative features to `` and mark them with + or - depending on whether they make sense. Example (In the example, we can see that the first feature makes sense while the second does not.): * peníze + * s - 1. Open classify.py, read the code, uncomment print statements, observe the results. 1. Why the classification is not very good even though the accuracy is over 95 %? Particularly, why the last sentence is not correctly classified? Write your answer at the end of ``. Feel free to discuss it with the group. 1. Think of improvements in feature extraction. Currently, the program takes only words as features. Add another feature, i.e. modify the function `document_features()`. === Sentiment analysis in English === Second, we try the Stanford Core NLP Sentiment Pipeline. Requirements: Java 8, python, gigabytes of memory `module add jdk` this adds Java 8, you can check it when typing `java -version` 1. Download Stanford Core NLP from http://nlp.stanford.edu/software/corenlp.shtml, unzip it. 2. Try it: e.g. `java -cp "stanford-corenlp-full-2015-04-20/*" -mx5g edu.stanford.nlp.sentiment.SentimentPipeline -stdin` or `java -cp "stanford-corenlp-full-2015-04-20/*" -mx5g edu.stanford.nlp.sentiment.SentimentPipeline -file book-reviews.txt` 3. In how many classes does Stanford Core NLP classify the sentences? Write it in ``. Write example of a wrong classification.