• Poonam Choudhari
• Dr.S.Veenadhari

Sentiment Analysis is a process to understand the feeling/attitude/sentiment towards a written piece of text by analyzing and then classifying the text as positive, negative or neutral. Data is one of the important aspect that should be handled and represented carefully in the classification process, which affects the performance of the classifier. In sentiment classification process data is represented as feature vector. Our work focuses on investigating the performance of Word2Vec N-grams (Uni grams and Bi grams) feature vector in the sentiment classification process of online consumer reviews about different products. The feature vector are tested on different well known text classifiers used for Sentiment Analysis .We also investigated the performance of feature vector as the size of data set is increased . Thus it would help to find optimal combination which could enhance the performance of classifier.

Sentiment Analysis ,Word2Vec ,CBOW, Skip-Gram, Random Forest, LRCV,MLP, Naïve Bayes, Decision Tree

"Sentiment Analysis of Online Product Reviews with Word2vec N-grams", International Journal of Emerging Technologies and Innovative Research (www.jetir.org), ISSN:2349-5162, Vol.6, Issue 4, page no.555-559, April-2019, Available :http://www.jetir.org/papers/JETIR1904P86.pdf

"Sentiment Analysis of Online Product Reviews with Word2vec N-grams", International Journal of Emerging Technologies and Innovative Research (www.jetir.org | UGC and issn Approved), ISSN:2349-5162, Vol.6, Issue 4, page no. pp555-559, April-2019, Available at : http://www.jetir.org/papers/JETIR1904P86.pdf