Hybrid Improved Document-level Embedding (HIDE)

TL;DR

HIDE is a novel hybrid embedding method that enhances document-level sentiment analysis by integrating domain, POS, and sentiment info into word embeddings, combined with LSA for improved accuracy.

Contribution

The paper introduces HIDE, a new hybrid embedding approach that incorporates multiple types of information into word embeddings and combines them with LSA for better sentiment analysis.

Findings

HIDE outperforms existing pretrained embeddings like GloVe and Word2Vec.

HIDE achieves higher accuracy on six datasets.

HIDE surpasses two existing document-level sentiment analysis methods.

Abstract

In recent times, word embeddings are taking a significant role in sentiment analysis. As the generation of word embeddings needs huge corpora, many applications use pretrained embeddings. In spite of the success, word embeddings suffers from certain drawbacks such as it does not capture sentiment information of a word, contextual information in terms of parts of speech tags and domain-specific information. In this work we propose HIDE a Hybrid Improved Document level Embedding which incorporates domain information, parts of speech information and sentiment information into existing word embeddings such as GloVe and Word2Vec. It combine improved word embeddings into document level embeddings. Further, Latent Semantic Analysis (LSA) has been used to represent documents as a vectors. HIDE is generated, combining LSA and document level embeddings, which is computed from improved word embeddings. We test HIDE with six different datasets and shown considerable improvement over the accuracy of existing pretrained word vectors such as GloVe and Word2Vec. We further compare our work with two existing document level sentiment analysis approaches. HIDE performs better than existing systems.