Cookies Policy
The website need some cookies and similar means to function. If you permit us, we will use those means to collect data on your visits for aggregated statistics to improve our service. Find out More
Accept Reject
  • Menu
About

About

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.

Interest
Topics
Details

Details

  • Name

    Pavel Brazdil
  • Role

    Research Coordinator
  • Since

    01st January 2010
001
Publications

2023

AfriSenti: A Twitter Sentiment Analysis Benchmark for African Languages

Authors
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;

Publication
CoRR

Abstract

2023

Exploring the Reduction of Configuration Spaces of Workflows

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

Publication
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

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

Publication
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

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

Publication
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

NLP-Crowdsourcing Hybrid Framework for Inter-Researcher Similarity Detection

Authors
Correia, A; Guimaraes, D; Paredes, H; Fonseca, B; Paulino, D; Trigo, L; Brazdil, P; Schneider, D; Grover, A; Jameel, S;

Publication
IEEE TRANSACTIONS ON HUMAN-MACHINE SYSTEMS

Abstract
Visualizing and examining the intellectual landscape and evolution of scientific communities to support collaboration is crucial for multiple research purposes. In some cases, measuring similarities and matching patterns between research publication document sets can help to identify people with similar interests for building research collaboration networks and university-industry linkages. The premise of this work is assessing feasibility for resolving ambiguous cases in similarity detection to determine authorship with natural language processing (NLP) techniques so that crowdsourcing is applied only in instances that require human judgment. Using an NLP-crowdsourcing convergence strategy, we can reduce the costs of microtask crowdsourcing while saving time and maintaining disambiguation accuracy over large datasets. This article contributes a next-gen crowd-artificial intelligence framework that used an ensemble of term frequency-inverse document frequency and bidirectional encoder representation from transformers to obtain similarity rankings for pairs of scientific documents. A sequence of content-based similarity tasks was created using a crowd-powered interface for solving disambiguation problems. Our experimental results suggest that an adaptive NLP-crowdsourcing hybrid framework has advantages for inter-researcher similarity detection tasks where fully automatic algorithms provide unsatisfactory results, with the goal of helping researchers discover potential collaborators using data-driven approaches.

Supervised
thesis

2021

High-speed and High-assurance Cryptographic Software

Author
Tiago Filipe Azevedo Oliveira

Institution
UP-FCUP

2021

High Definition Wireless Video Streaming  using Underwater Data Mules

Author
João Pedro Teixeira Loureiro

Institution
UP-FEUP

2020

Identification of Microservices from Monolithic Applications through Topic Modelling

Author
Miguel António Ferrão Brito

Institution
UM

2020

Peer-production and Technology-enhanced Collaborative Teaching and Learning (Models, Methods and Framework)

Author
sara dos Santos Fernandes

Institution
UP-FCUP

2020

Augmented Reality over Maps

Author
Miguel Jorge da Lomba Magalhães

Institution
UM