Enhancing Sentiment Analysis with Word2Vec and LSTM: A Comparative Study
Haodong Tang
Qianjiang College, Hangzhou Normal University, Hangzhou, 310018, China.
Nan Zhang
Qianjiang College, Hangzhou Normal University, Hangzhou, 310018, China.
Xinyi Yu
Qianjiang College, Hangzhou Normal University, Hangzhou, 310018, China.
Tengze Mao
Qianjiang College, Hangzhou Normal University, Hangzhou, 310018, China.
Lidong Wang *
Qianjiang College, Hangzhou Normal University, Hangzhou, 310018, China.
*Author to whom correspondence should be addressed.
Abstract
Sentiment analysis is an important natural language processing task that helps people understand the emotional information conveyed in texts. This paper aims to propose a sentiment classification model based on the combination of Word2Vec and LSTM (Long Short Term Memory). This paper will introduce two key technologies, Word2Vec and LSTM, combining them to build an effective sentiment analysis model. We conducted a comparative analysis between our model and other state-of-the-art methods including CNN, BiLSTM+CNN, Word2vec+SVM, among others. Through rigorous experimental evaluation, this paper showcases the effectiveness and superior performance of the proposed model in sentiment classification tasks. Our method attains an F1 score of 78.2% on benchmark dataset, indicating its strong performance in the task.
Keywords: Word2Vec, LSTM, sentiment analysis, deep neural network, convolutional neural network