Repository logo
 
Profile Picture
Person

Laroca Mendes Pinto, Herbert

Metadata only
0000-0002-0362-6100

Filters

2019 - 201912020 - 20241
Reset filters

Settings

Search Results

Now showing 1 - 2 of 2
  • Combining sentiment analysis scores to improve accuracy of polarity classification in MOOC posts
    Publication . Laroca, Herbert; Rocio, Vitor
    Sentiment analysis is a set of techniques that deal with the verification of sentiment and emotions in written texts. This introductory work aims to explore the combination of scores and polarities of sentiments (positive, neutral and negative) provided by different sentiment analysis tools. The goal is to generate a final score and its respective polarity from the normalization and arithmetic average scores given by those tools that provide a minimum of reliability. The texts analyzed to test our hypotheses were obtained from forum posts from participants in a massive open online course (MOOC) offered by Universidade Aberta de Portugal, and were submitted to four online service APIs offering sentiment analysis: Amazon Comprehend, Google Natural Language, IBM Watson Natural Language Understanding, and Microsoft Text Analytics. The initial results are encouraging, suggesting that the average score is a valid way to increase the accuracy of the predictions from different sentiment analyzers.
    2019-09Conference object Restricted access Show more
  • Does fake news have feelings?
    Publication . Laroca Mendes Pinto, Herbert; Rocio, Vitor; Cunha, António
    Fake news spreads rapidly, creating issues and making detection harder. The purpose of this study is to determine if fake news contains sentiment polarity (positive or negative), identify the polarity of sentiment present in their textual content and determine whether sentiment polarity is a reliable indication of fake news. For this, we use a deep learning model called BERT (Bidirectional Encoder Representations from Transformers), trained on a sentiment polarity dataset to classify the polarity of sentiments from a dataset of true and fake news. The findings show that sentiment polarity is not a reliable single feature for recognizing false news correctly and must be combined with other parameters to improve classification accuracy.
    2024Journal article Open access Show more