Sentiment analysis is the task of classifying the polarity of a given text. For instance, a text-based tweet can be categorized as either "positive," "negative," or "neutral". Given the text and accompanying labels, a model can be trained to predict the correct sentiment. Sentiment analysis techniques can be categorized into machine learning, lexicon-based, and even hybrid methods. Some subcategories of research in sentiment analysis include multimodal sentiment analysis, aspect-based sentiment analysis, fine-grained opinion analysis, and language-specific sentiment analysis. Sentiment Analysis using LSTM
-
Implement a sentiment analysis using the single layer Bi-LSTM model. You are free to decide the hidden dimension and all other hyper-parameters in the network. Also choose proper error function for this task.
-
You can use FastText/Glove/word2vec and pre-trained embedding to initialize the model.
F1 score (For evaluating all the models)
Split the dataset into train(80%), dev(10%) and test(10%) and perform the experiment.
Submission Materials: Python file, Google drive link for the trained model, a doc-file with results, and your observation.