Skip to content

RizzWann/Sentiment-Analysis-Using-ML-Models

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

7 Commits
 
 
 
 
 
 
 
 
 
 

Repository files navigation

Sentiment-Analysis

Q1) Word similarity

Improve the similarity function for matching query entered by user with a predefined list of bank names. An example is given in the attached code.

Q2)Sentiment Analysis

(a) Prepare a Roman Urdu dataset for multiclass classification (sentiment analysis) Scrap roman Urdu tweets from Twitter using some Roman Urdu keywords on some topic of your choice. Scrap around 500 tweets on your topic and label them into five classes (very negative, negative, neutral, positive, very positive).

(b) Build sentiment classifiers using bag of words and ngram model for the dataset created in part (a). You can use scikit-learn (machine learning tool for python) for using implementations of classification algorithms. Perform multiclass classification. For multi class you have to classify the tweets into one of the five categories (very negative, negative, neutral, positive, very positive). Split the data into train and test set by using “train_test_split(DataSet)” of scikit. Implement following feature extraction methods. Bag of words based on raw counts Bag of words based on TfIDF ngrams (unigrams, bigrams, trigrams)

About

Roman Urdu Sentiment Anaylsis

Resources

License

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published