![2.2 Language Model
Unigram
The word vectors
are taken
individually to train.
E.g: I am not dexter.
Is taken as:
[I, am, not, dexter]
Bigram
The word vectors
are taken two at a
time to train.
E.g: I am not dexter.
Is taken as:
[(I,am), (am,not),
(not,dexter)]
Unigram + Bigram
Use unigram
normally but bigram
when words
reversing sentiments
like not,no,etc are
present.
E.g: I am not dexter.
Is taken as:
[I,am,(not,dexter)]](https://image.slidesharecdn.com/sentimentanalysis-160411150113/85/Sentiment-analysis-of-Twitter-Data-11-320.jpg)
Sentiment analysis of Twitter Data
- 1. Sentiment Analysis of Twitter Data
- 2. Hello! We are Team 10 Member 1: Name: Nurendra Choudhary Roll Number: 201325186 Member 2: Name: P Yaswanth Satya Vital Varma Roll Number: 201301064
- 3. Introduction: Twitter is a popular microblogging service where users create status messages (called "tweets"). These tweets sometimes express opinions about different topics. Generally, this type of sentiment analysis is useful for consumers who are trying to research a product or service, or marketers researching public opinion of their company.
- 4. AIM OF THE PROJECT The purpose of this project is to build an algorithm that can accurately classify Twitter messages as positive or negative, with respect to a query term. Our hypothesis is that we can obtain high accuracy on classifying sentiment in Twitter messages using machine learning techniques.
- 5. The details of the dataset used for training the Classifier. 1. Dataset
- 6. 1600000 sentences annotated as positive, negative. http://help.sentiment140.com/for-students/ Sentiment140 Dataset
- 7. Pre-Processing the raw data to increase ease for the classifier. 2. Pre-Processing
- 8. ➜ Case Folding of the Data (Turning everything to lowercase) ➜ Punctuation Removal from the data ➜ Common Abbreviations and Acronyms expanded. ➜ HashTag removal. Steps in Preprocessing:
- 9. Includes Language Models (Unigram,Bigram), Lexical Scoring, Machine Learning Scores, Emoticon Scores. 2. The Main System
- 10. 2.1 Training Distributed Semantic Representation (Word2Vec Model) ➜ We use a Python Module called gensim. models.word2vec for this. ➜ We train a model using only the sentences (after preprocessing) from the corpus. ➜ This generates vectors for all the words in the corpus. ➜ This model can now be used to get vectors for the words. ➜ For unknown words, we use the vectors of words with frequency one.
- 11. 2.2 Language Model Unigram The word vectors are taken individually to train. E.g: I am not dexter. Is taken as: [I, am, not, dexter] Bigram The word vectors are taken two at a time to train. E.g: I am not dexter. Is taken as: [(I,am), (am,not), (not,dexter)] Unigram + Bigram Use unigram normally but bigram when words reversing sentiments like not,no,etc are present. E.g: I am not dexter. Is taken as: [I,am,(not,dexter)]
- 12. 2.3 Training For Machine Learning Scores 1. Use the various language models and train various two-class classifiers for results. 2. The classifiers we used are: a. Support Vector Machines - Scikit Learn Python b. Multi Layer Perceptron Neural Network - Scikit Learn Python c. Naive Bayes Classifier - Scikit Learn Python d. Decision Tree Classifier - Scikit Learn Python e. Random Forest Classifier - Scikit Learn Python f. Logistic Regression Classifier - Scikit Learn Python g. Recurrent Neural Networks - PyBrain module Python
- 13. Logistic Regression: Logistic regression is a powerful statistical way of modeling a binomial outcome (takes the value 0 or 1 like having or not having a disease) with one or more explanatory variables. Naive Bayes Classifier: Try solving the problem with a simple classifier. Multi-Layer Perceptron Neural Network Classifier: The method has significantly increased results in binary classification compared to classical classifiers. Recurrent Neural Networks: This class of neural networks have significantly improved results for various Natural Language Processing Problems. Hence, this was tried too. 2.3.1 Reasons for using the Classifiers
- 14. Decision Trees: Decision trees are very intuitive and easy to explain. Decision trees do not require any assumptions of linearity in the data. Random Forest: Decision Trees tend to overfit. Hence an ensemble of them gives a much better output for unseen data. Support Vector Machines: This classifier has been proven by a lot of research papers to give the best result among the classical classifiers. 2.3.1 Reasons for using the Classifiers
- 15. 2.3.2 Accuracies of Various Approaches (Accuracies are calculated using 5-fold cross-validation) Unigram Bigram Unigram + Bigram Support Vector Machines 71.1% -NA- (Takes too much time to train, stopped after 28 hours) 74.3% Naive Bayes Classifier 64.2% 62.8% 65.0% Logistic Regression 67.4% 72.1% 71.6%
- 16. 2.3.2 Accuracies of Various Approaches (Accuracies are calculated using 5-fold cross-validation) Unigram Bigram Unigram + Bigram Decision Trees 60.4% 60.0% 61.5% Random Forest Classifier 67.1% 70.8% 71.3% Multi-Perceptron Neural Network Classifier 68.6% 72.7% 74%
- 17. 2.3.2 Accuracies of Various Approaches (Accuracies are calculated using 5-fold cross-validation) Unigram Bigram Unigram + Bigram Recurrent Neural Networks 69.1% 70.4% 71.5%
- 18. 2.3.4 Based on the Above Results: We chose Unigram+Bigram with Random Forest Classifier to be the part of our system as they gave the best results.
- 19. Emoticons play a major role in deciding the sentiment of a sentence, hence Emoticon Scoring
- 20. Emoticon Scoring Use a dictionary to score the emoticons. Use this emoticon score in the model. Search for Emoticons in the given text using RegEx or find.
- 21. Get the text Lexical Scoring (Scoring based on words of the text) Lemmatize the text The Score will be used in the final system. This will be given more weightage as this is more definite Score the Lemmatized text using dictionaries
- 22. Training Classifier and Word2Vec Model Preprocessing Train Word2Vec Model Annotated Training Data Sentence VectorSentences Classifier ModelTrain using various classifier algorithms
- 23. The Overall Scoring Process Goes Like This Lexical Scores Classifier Scores Emoticon Scores Unigram Bigram Sentences Overall Scores Weight of Lexical Scores Weight of Emoticons
- 24. Challenges in the Approach Randomness in Data Twitter is written by Users, hence it is not very formal. Emoticons Lots of types of emoticons with new ones coming very frequently. Abbreviations Users use a lot of abbreviation slangs like AFAIK, GN, etc. Capturing all of them is difficult. Grapheme Stretching Emotions expressed through stretching of normal words. Like, Please -> Pleaaaaaseeeeee Reversing Words Some words completely reverse sentiment of another word. E.g: not good == opposite(good) Technical Challenges Classifiers take a lot of time to train, hence silly mistakes cost a lot of time.
- 25. Future Improvements ➜ Handle Grapheme Stretching ➜ Handle authenticity of Data and Users ➜ Handle Sarcasm and Humor
- 26. Thanks! Github Link to the Project: https://github.com/Akirato/Twitter-Sentiment-Analysis-Tool Any questions? You can mail us at: nurendra.choudhary@research.iiit.ac.in Or satyavital.varma@students.iiit.ac.in