Concept of TF-IDF, Common Bag of Word and Word Embedding for Effective Sentiment Classification
Swamy L N1, J V Gorabal2

1Swamy L N*, Research Scholar, Department of CSE, Sahyadri College of Engineering & Management, VTU-Belagavi, Mangalore, Karnataka, India.
2Dr. J V Gorabal, Department of Computer Science & Engineering, Sahyadri College of Engineering & Management, Mangalore, Karnataka, India.
Manuscript received on March 15, 2020. | Revised Manuscript received on March 31, 2020. | Manuscript published on April 10, 2020. | PP: 2198-2201 | Volume-9 Issue-6, April 2020. | Retrieval Number: F4582049620/2020©BEIESP | DOI: 10.35940/ijitee.F4582.049620
Open Access | Ethics and Policies | Cite | Mendeley
© The Authors. Blue Eyes Intelligence Engineering and Sciences Publication (BEIESP). This is an open access article under the CC BY-NC-ND license (

Abstract: Sentiment Classification is one of the well-known and most popular domain of machine learning and natural language processing. An algorithm is developed to understand the opinion of an entity similar to human beings. This research fining article presents a similar to the mention above. Concept of natural language processing is considered for text representation. Later novel word embedding model is proposed for effective classification of the data. Tf-IDF and Common BoW representation models were considered for representation of text data. Importance of these models are discussed in the respective sections. The proposed is testing using IMDB datasets. 50% training and 50% testing with three random shuffling of the datasets are used for evaluation of the model. 
Keywords: Sentiment Analysis, Word Embedding, Machine Learning.
Scope of the Article: Machine Learning.