Cookies
O website necessita de alguns cookies e outros recursos semelhantes para funcionar. Caso o permita, o INESC TEC irá utilizar cookies para recolher dados sobre as suas visitas, contribuindo, assim, para estatísticas agregadas que permitem melhorar o nosso serviço. Ver mais
Aceitar Rejeitar
  • Menu
Sobre

Sobre

Pavel Brazdil is a founder of a strong Machine Learning / Data Mining group that exists since 1988 and which now is a part of LIAAD Inesc Tec (Laboratory of AI and Decision Support). Pavel Brazdil is Full Professor (Prof. Catedrático) at the Faculty of Economics (FEP) of University of Porto, where he has been teaching courses on Information systems, Data Mining and Text Mining. He has supervised 12 PhD students. Although he has officially retired in mid-July 2015, he continues his R&D activities, including teaching at Master and Doctoral courses and supervision of post-graduate students.

Tópicos
de interesse
Detalhes

Detalhes

  • Nome

    Pavel Brazdil
  • Cargo

    Investigador Coordenador
  • Desde

    01 janeiro 2010
  • Nacionalidade

    República Checa
  • Contactos

    +351220402963
    pavel.brazdil@inesctec.pt
001
Publicações

2023

AfriSenti: A Twitter Sentiment Analysis Benchmark for African Languages

Autores
Muhammad, SH; Abdulmumin, I; Ayele, AA; Ousidhoum, N; Adelani, DI; Yimam, SM; Ahmad, IS; Beloucif, M; Mohammad, S; Ruder, S; Hourrane, O; Brazdil, P; António Ali, FDM; David, D; Osei, S; Bello, BS; Ibrahim, F; Gwadabe, T; Rutunda, S; Belay, TD; Messelle, WB; Balcha, HB; Chala, SA; Gebremichael, HT; Opoku, B; Arthur, S;

Publicação
CoRR

Abstract

2023

Exploring the Reduction of Configuration Spaces of Workflows

Autores
Freitas, F; Brazdil, P; Soares, C;

Publicação
Discovery Science - 26th International Conference, DS 2023, Porto, Portugal, October 9-11, 2023, Proceedings

Abstract
Many current AutoML platforms include a very large space of alternatives (the configuration space) that make it difficult to identify the best alternative for a given dataset. In this paper we explore a method that can reduce a large configuration space to a significantly smaller one and so help to reduce the search time for the potentially best workflow. We empirically validate the method on a set of workflows that include four ML algorithms (SVM, RF, LogR and LD) with different sets of hyperparameters. Our results show that it is possible to reduce the given space by more than one order of magnitude, from a few thousands to tens of workflows, while the risk that the best workflow is eliminated is nearly zero. The system after reduction is about one order of magnitude faster than the original one, but still maintains the same predictive accuracy and loss. © 2023, The Author(s), under exclusive license to Springer Nature Switzerland AG.

2023

Combining Symbolic and Deep Learning Approaches for Sentiment Analysis

Autores
Muhammad, SH; Brazdil, P; Jorge, A;

Publicação
Compendium of Neurosymbolic Artificial Intelligence

Abstract
Deep learning approaches have become popular in sentiment analysis because of their competitive performance. The downside of this approach is that they do not provide understandable explanations on how the sentiment values are calculated. Previous approaches that used sentiment lexicons for sentiment analysis can do that, but their performance is lower than deep learning approaches. Therefore, it is natural to wonder if the two approaches can be combined to exploit their advantages. In this chapter, we present a neuro-symbolic approach that combines both symbolic and deep learning approaches for sentiment analysis tasks. The symbolic approach exploits sentiment lexicon and shifter patterns-which cover the operations of inversion/reversal, intensification, and attenuation/downtoning. The deep learning approach used a pre-trained language model (PLM) to construct sentiment lexicon. Our experimental result shows that the proposed approach leads to promising results, substantially better than the results of a pure lexicon-based approach. Although the results did not reach the level of the deep learning approach, a great advantage is that sentiment prediction can be accompanied by understandable explanations. For some users, it is very important to see how sentiment is derived, even if performance is a little lower. © 2023 The authors and IOS Press. All rights reserved.

2023

Combining symbolic and deep learning approaches for sentiment analysis

Autores
Muhammad, SH; Brazdil, P; Jorge, A;

Publicação
Frontiers in Artificial Intelligence and Applications

Abstract
Deep learning approaches have become popular in sentiment analysis because of their competitive performance. The downside of this approach is that they do not provide understandable explanations on how the sentiment values are calculated. Previous approaches that used sentiment lexicons for sentiment analysis can do that, but their performance is lower than deep learning approaches. Therefore, it is natural to wonder if the two approaches can be combined to exploit their advantages. In this chapter, we present a neuro-symbolic approach that combines both symbolic and deep learning approaches for sentiment analysis tasks. The symbolic approach exploits sentiment lexicon and shifter patterns-which cover the operations of inversion/reversal, intensification, and attenuation/downtoning. The deep learning approach used a pre-trained language model (PLM) to construct sentiment lexicon. Our experimental result shows that the proposed approach leads to promising results, substantially better than the results of a pure lexicon-based approach. Although the results did not reach the level of the deep learning approach, a great advantage is that sentiment prediction can be accompanied by understandable explanations. For some users, it is very important to see how sentiment is derived, even if performance is a little lower. © 2023 The authors and IOS Press. All rights reserved.

2023

Symbolic Versus Deep Learning Techniques for Explainable Sentiment Analysis

Autores
Muhammad, SH; Brazdil, P; Jorge, A;

Publicação
Progress in Artificial Intelligence - 22nd EPIA Conference on Artificial Intelligence, EPIA 2023, Faial Island, Azores, September 5-8, 2023, Proceedings, Part I

Abstract
Deep learning approaches have become popular in many different areas, including sentiment analysis (SA), because of their competitive performance. However, the downside of this approach is that they do not provide understandable explanations on how the sentiment values are calculated. In contrast, previous approaches that used sentiment lexicons can do that, but their performance is normally not high. To leverage the strengths of both approaches, we present a neuro-symbolic approach that combines deep learning (DL) and symbolic methods for SA tasks. The DL approach uses a pre-trained language model (PLM) to construct sentiment lexicon. The symbolic approach exploits the constructed sentiment lexicon and manually constructed shifter patterns to determine the sentiment of a sentence. Our experimental results show that the proposed approach leads to promising results with the additional advantage that sentiment predictions can be accompanied by understandable explanations.

Teses
supervisionadas

2017

Automatic Recommendation of Machine Learning Workflows

Autor
Miguel Alexandre Viana Cachada

Instituição
UP-FEP

2017

Improving Algorithm Selection Methods using Meta-Learning by Considering Accuracy and Run Time

Autor
Salisu Mamman Abdulrahman

Instituição
UP-FEP

2017

Identifying Affinity Groups of Researchers in FEP through the Application of Community Detection Algorithms

Autor
André Martinez Candeias Lima

Instituição
UP-FEP

2017

Workflow Recommendation for Text Classification Problems

Autor
Maria João Fernandes Ferreira

Instituição
UP-FCUP

2015

Geração Sintética de Microdados utilizando algorítmos de datamining

Autor
Daniel Fernando Alves da Silva

Instituição
UP-FEP