Simple Search:

Effective method for sentiment lexical dictionary enrichment based on Word2Vec for sentiment analysis


Citation

Alshari, Eissa Mohammed Mohsen and Azman, Azreen and C. Doraisamy, Shyamala and Mustapha, Norwati and Alksher, Mostafa Ahmed (2018) Effective method for sentiment lexical dictionary enrichment based on Word2Vec for sentiment analysis. In: 2018 Fourth International Conference on Information Retrieval and Knowledge Management (CAMP'18), 26-28 Mar. 2018, Le Méridien Kota Kinabalu,Sabah, Malaysia. (pp. 177-181).

Abstract / Synopsis

Recently, many researchers have shown interest in using lexical dictionary for sentiment analysis. The SentiWordNet is the most used sentiment lexical to determine the polarity of texts. However, there are huge number of terms in the corpus vocabulary that are not in the SentiWordNet due to the curse of dimensionality, which will limit the performance of the sentiment analysis. This paper proposed a method to enlarge the size of opinion words by learning the polarity of those non-opinion words in the vocabulary based on the SentiWordNet. The effectiveness of the method is evaluated by using the Internet Movie Review Dataset. The result is promising, showing that the proposed Senti2Vec method can be more effective than the SentiWordNet as the sentiment lexical resource.


Download File

[img]
Preview
PDF (Abstract)
Effective method for sentiment lexical dictionary enrichment based on Word2Vec for sentiment analysis.pdf

Download (35kB) | Preview

Additional Metadata

Item Type: Conference or Workshop Item (Paper)
Divisions: Faculty of Computer Science and Information Technology
DOI Number: https://doi.org/10.1109/INFRKM.2018.8464775
Publisher: IEEE
Keywords: Sentiment analysis; Word2Vec; Word embeddings; SentiWordNet
Depositing User: Nabilah Mustapa
Date Deposited: 10 Jun 2019 10:41
Last Modified: 10 Jun 2019 10:41
Altmetrics: http://www.altmetric.com/details.php?domain=psasir.upm.edu.my&doi=10.1109/INFRKM.2018.8464775
URI: http://psasir.upm.edu.my/id/eprint/68521
Statistic Details: View Download Statistic

Actions (login required)

View Item View Item