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

Abstract

Perceived quality and value are very essential attributes in the context of brand management. These attributes are traditionally measured using primary surveys. In this work, we propose a methodology to estimate perceived quality and value from online consumer reviews using aspect-based sentiment analysis. We crawled reviews of five popular mobile brands from a reputed e-commerce website. We have applied state-of-the-art text pre-processing techniques to clean the text and to extract the aspects using a semi-automatic approach using dependency parser. The aspects are categorized into five clusters in relevance with benefits consumers get from the brand. Lastly, we have applied TOPSIS, a multi-criterion decision-making algorithm, to rank the brands based on perceived quality scores.