124 documents found, page 1 of 13
Lexicon annotation with LLM: a proof of concept with ChatGPT
Marcondes, Francisco Supino; Gala, Adelino de C.O.S.; Rodrigues, Manuel; Almeida, J. J.; Novais, PauloLexicon annotation is a critical yet time-consuming task that can hold back the progress of language-intensive projects. This paper explores the potential of Large Language Models (LLMs) to automate lexicon annotation, traditionally performed by humans. We present a proof of concept by evaluating ChatGPT's performance on annotating VADER's sentiment lexicon. Our findings demonstrate that ChatGPT achieves fair p...
Emotional and mental nuances and technological approaches: Optimising Fact-Chec...
Marcondes, Francisco S.; Barbosa, Maria Araújo; Gala, Adelino de C. O. S.; Almeida, J. J.; Novais, PauloThe issue of the dissemination of fake news has been widely addressed in the literature, but the issue of the dissemination of fact checks to debunk fake news has not received sufficient attention. Fake news is tailored to reach a wide audience, a concern that, as this paper shows, does not seem to be present in fact checking. As a result, fact checking, no matter how good it is, fails in its goal of debunking ...
Automatic exercise generation for exploring connections between mathematics and...
Brito, Irene; Almeida, J. J.; Machado, Gaspar J.Mathematics and Music are closely connected and their multifaceted relationship has been explored since ancient times. Pythagoras was one of the first who discovered and formalized one of those connections by studying the arithmetic of musical intervals, expressing them by numerical ratios and relating ratios to consonance/dissonance notions, being the Pythagorean tuning and scale based on arithmetic principles...
SE4AI issues on social media agent design with use cases
Novais, Paulo; Marcondes, Francisco Supino; Almeida, J. J.This paper is the result of an endeavor of specifying a social media agent through Use Case 2.0 (the “agile Use Case”). That what was expected to be a straightforward specification task revealed issues that subverts a critical foundation of the Use Case conception, nonexistent use-case between the SuD and the actor, yielding to the extensions proposed in this paper.
An exploratory design science research on troll factories
Marcondes, Francisco Supino; Almeida, J. J.; Novais, PauloPrivate and military troll factories (facilities used to spread rumours in online social media) are currently proliferating around the world. By their very nature, they are obscure companies whose internal workings are largely unknown, apart from leaks to the press. They are even more concealed when it comes to their underlying technology. At least in a broad sense, it is believed that there are two main tasks ...
Large language models: compilers for the 4th generation of programming languages?
Marcondes, Francisco Supino; Almeida, J. J.; Novais, PauloThis paper explores the possibility of large language models as a fourth generation programming language compiler. This is based on the idea that large language models are able to translate a natural language specification into a program written in a particular programming language. In other words, just as high-level languages provided an additional language abstraction to assembly code, large language models c...
Designing and randomising multiple-choice questions for e-learning in mathemati...
Brito, Irene; Machado, Gaspar J.; Almeida, J. J.MVGEN is a multi-version question generation tool, which allows creating multiple-choice questions with a large number of versions and multi-version tests using different randomisation techniques. These techniques include simple randomisation through shuffling of lists with keys and distractors or random selection of options from lists with several keys and distractors, but also more complex randomisation of pa...
Automation of social media interactions: a framework for online social “sowing”
Marcondes, Francisco S.; Almeida, J. J.; Novais, PauloA fundamental behavior in social agents is to start, keep and grow its target network, this is called “sowing” and depends on affective computing principles, methods and tools. This paper evaluates the feasibility of sowing being fully or partially automated. The discussion is grounded on a framework elaboration that addresses key-issues of such a behavior. The framework construction strengthens the case for it...
Neural network eXplainable AI based on paraconsistent analysis - an initial app...
Marcondes, Francisco S.; Durães, Dalila; Gomes, Marco Filipe Vieira; Santos, Flávio; Almeida, J. J.; Novais, PauloPara-consistent logic is a non-classical logic whose foundations allow the treatment of contradictions without invalidating the conclusions. This paper presented an attempt of using Annotated Para-consistent Analysis (APA) for supporting eXplained Artificial Intelligence (XAI) on Neural-Networks. For the study case, it was presented a situation where a binary classification model was able to correctly recognize...
Neural network explainable AI based on paraconsistent analysis: an extension
Marcondes, Francisco Supino; Durães, Dalila; Santos, Flávio Arthur Oliveira; Almeida, J. J.; Novais, PauloThis paper explores the use of paraconsistent analysis for assessing neural networks from an explainable AI perspective. This is an early exploration paper aiming to understand whether paraconsistent analysis can be applied for understanding neural networks and whether it is worth further develop the subject in future research. The answers to these two questions are affirmative. Paraconsistent analysis provides...