Bianca Lima Santos

This systematic review investigates the application of machine learning in facial expressions and emotion recognition within the realm of experience (UX). The main objective is to identify advances in the state of the art regarding using facial expressions to detect emotions and, consequently, predict or improve experience. The methodology provided a comprehensive analysis of existing literature, highlighting diverse definitions of UX and their implications for assessing … Mostrar más

This systematic review investigates the application of machine learning in facial expressions and emotion recognition within the realm of experience (UX). The main objective is to identify advances in the state of the art regarding using facial expressions to detect emotions and, consequently, predict or improve experience. The methodology provided a comprehensive analysis of existing literature, highlighting diverse definitions of UX and their implications for assessing interactions with systems. Despite efforts to evaluate and enhance UX through various methodologies, few studies focus on predicting UX by integrating emotional states before interaction and -reported experiences. This gap stems from the absence of a unified UX definition, complicating methodological standardization and result comparability across studies. Many reviewed works emphasize developing recommendation algorithms tailored to music, news, and other content to optimize UX through emotional data. The review identified the challenge of establishing a consistent framework for UX definition across research, revealing varied approaches using different datasets aimed at enhancing recommendations, improving satisfaction, comparing perceived attitudes, and integrating with established questionnaires. Mostrar menos

In recent years, we have seen an expressive increase in the number of s participating in social networks. Social networks, in general, have proven to be quite effective in spreading opinions and influencing people as messages can be shared with thousands of people in a few minutes. However, this ability has been exploited in a negative way, to manipulate opinions and spread misinformation and/or fake news. A common way of doing this is through the use of bots, computer algorithms that mimic… Mostrar más

In recent years, we have seen an expressive increase in the number of s participating in social networks. Social networks, in general, have proven to be quite effective in spreading opinions and influencing people as messages can be shared with thousands of people in a few minutes. However, this ability has been exploited in a negative way, to manipulate opinions and spread misinformation and/or fake news. A common way of doing this is through the use of bots, computer algorithms that mimic human behavior, disseminating topics and news, demonstrating or rejection to personalities, and interacting with other s, which can impact even democratic discussions. For this reason, the present work aims to show and compare approaches for detecting social bots using Twitter ’s posts data extracted during the Brazilian presidential election period of 2018. Using a dataset of Twitter s labeled as bots or humans, this research applies five natural language processing (NLP) techniques to extract characteristics from the content of the ’s messages on the social network. In order to analyze the impact of features extracted through NLP in the task of detecting bots, five different classifiers were tested including pre-processing techniques and feature selection. The best results were achieved through a union of all the extracted features using the Random Forest classifier, achieving an accuracy of 0.91 for the bot class and AUC of 0.83. Mostrar menos

The use of social bots for political purposes has become an increasingly relevant concern and has raised warnings aboutthe impact on democratic discussions. This paper presents a case study on the use of bots in political discussions duringthe second round of the 2018 Brazilian elections, aiming to build an automatic detection model for bots and comparingthe use of explainable and non-explainable artificial intelligence algorithms. First, a dataset was built by manuallylabeling s as bots… Mostrar más

The use of social bots for political purposes has become an increasingly relevant concern and has raised warnings aboutthe impact on democratic discussions. This paper presents a case study on the use of bots in political discussions duringthe second round of the 2018 Brazilian elections, aiming to build an automatic detection model for bots and comparingthe use of explainable and non-explainable artificial intelligence algorithms. First, a dataset was built by manuallylabeling s as bots or humans. Then linear regression algorithms, random trees, naive Bayesian, multilayerperceptron, and random forest were applied. It was identified that even simple and explainable algorithms, such asrandom tree, perform similarly to more complex algorithms such as random forest. Using only ’s characteristics, itwas possible to identify more than 46% of the bots, but all models showed a precision not greater than 52% in this task. Mostrar menos