Investigating the role of Word Embeddings in sentiment analysis

Authors

  • Samuele Martinelli Department of Theoretical and Applied Science, Insubria University, Varese, Italy
  • Gloria Gonella Department of Theoretical and Applied Science, Insubria University, Varese, Italy
  • Dario Bertolino Department of Theoretical and Applied Science, Insubria University, Varese, Italy

DOI:

https://doi.org/10.25081/imrj.2020.v10.6476

Keywords:

Natural language processing (NLP)

Abstract

During decades, Natural language processing (NLP) expanded its range of tasks, from document classification to automatic text summarization, sentiment analysis, text mining, machine translation, automatic question answering and others. In 2018, T. Young described NLP as a theory-motivated range of computational techniques for the automatic analysis and representation of human language. Outside and before AI, human language has been studied by specialists from various disciplines: linguistics, philosophy, logic, psychology. The aim of this work is to build a neural network to perform a sentiment analysis on Italian reviews from the chatbot customer service. Sentiment analysis is a data mining process which identifies and extracts subjective information from text. It could help to understand the social sentiment of clients, respect a business product or service. It could be a simple classification task that analyses a sentence and tells whether the underlying sentiment is positive or negative. The potentiality of deep learning techniques made this simple classification task evolve, creating new, more complex sentiment analysis, e.g. Intent Analysis and Contextual Semantic Search.

Downloads

Download data is not yet available.

Published

14-09-2020

How to Cite

Martinelli, S., G. Gonella, and D. Bertolino. “Investigating the Role of Word Embeddings in Sentiment Analysis”. International Multidisciplinary Research Journal, vol. 10, no. 2, Sept. 2020, pp. 18-24, doi:10.25081/imrj.2020.v10.6476.