Scientific paper resulting from the work of Mateus Alex dos Santos Luna. Published at the XVIII Encontro Nacional de Inteligência Artificial e Computacional, titled “Vector space models for trace clustering: a comparative study” and presented by Mateus in an online session. The paper features collaboration from researchers MSc. André Paulino Lima, MSc. Thaís Rodrigues Neubauer, Prof. Dr. Marcelo Fantinato and Prof. Dr. Sarajane Marques Peres (Mateus’s advisor). This work won second place in the “Best Papers” award in the undergraduate work track.
Abstract: Process mining explores event logs to offer valuable insights to business process managers. Some types of business processes are hard to mine, including unstructured and knowledge-intensive processes. Then, trace clustering is usually applied to event logs aiming to break it into sublogs, making it more amenable to the typical process mining task. However, applying clustering algorithms involves decisions, such as how traces are represented, that can lead to better results. In this paper, we compare four vector space models for trace clustering, using them with an agglomerative clustering algorithm in synthetic and real-world event logs. Our analyses suggest the embeddings-based vector space model can properly handle trace clustering in unstructured processes.
Complete paper here.
Mateus was part of the CNPq’s scientific initiation program and thanks the agency for the support provided during the research process.
Reference: Luna, M., Lima, A., Neubauer, T., Fantinato, M., & Peres, S. (2021). Vector space models for trace clustering: a comparative study. In Anais do XVIII Encontro Nacional de Inteligência Artificial e Computacional, (pp. 446-457). Porto Alegre: SBC. doi:10.5753/eniac.2021.18274
Bibtex:
@inproceedings{Luna2021,
author = {Mateus Luna and André Lima and Thaís Neubauer and Marcelo Fantinato and Sarajane Peres},
title = {Vector space models for trace clustering: a comparative study},
booktitle = {Anais do XVIII Encontro Nacional de Inteligência Artificial e Computacional},
location = {Evento Online},
year = {2021},
keywords = {},
issn = {2763-9061},
pages = {446–457},
publisher = {SBC},
address = {Porto Alegre, RS, Brasil},
doi = {10.5753/eniac.2021.18274},
url = {https://sol.sbc.org.br/index.php/eniac/article/view/18274}}
Artigo científico resultante do trabalho de Mateus Alex dos Santos Luna. Publicado no XVIII Encontro Nacional de Inteligência Artificial e Computacional, intitulado “Vector space models for trace clustering: a comparative study” e apresentado por Mateus em sessão online. O artigo foi escrito por Mateus com a colaboração de: MSc. André Paulino Lima, MSc. Thaís Rodrigues Neubauer, Prof. Dr. Marcelo Fantinato and Prof. Dr. Sarajane Marques Peres (orientadora). Este trabalho obteve o segundo lugar no prêmio de “melhores artigos” da trilha de trabalhos de graduação.
Artigo completo aqui – em ingles.
O Mateus fez parte do programa de iniciação científica do CNPq e agrade a agência pelo suporte fornecido durante a realização da pesquisa.
Referência: Luna, M., Lima, A., Neubauer, T., Fantinato, M., & Peres, S. (2021). Vector space models for trace clustering: a comparative study. In Anais do XVIII Encontro Nacional de Inteligência Artificial e Computacional, (pp. 446-457). Porto Alegre: SBC. doi:10.5753/eniac.2021.18274
Bibtex:
@inproceedings{Luna2021,
author = {Mateus Luna and André Lima and Thaís Neubauer and Marcelo Fantinato and Sarajane Peres},
title = {Vector space models for trace clustering: a comparative study},
booktitle = {Anais do XVIII Encontro Nacional de Inteligência Artificial e Computacional},
location = {Evento Online},
year = {2021},
keywords = {},
issn = {2763-9061},
pages = {446–457},
publisher = {SBC},
address = {Porto Alegre, RS, Brasil},
doi = {10.5753/eniac.2021.18274},
url = {https://sol.sbc.org.br/index.php/eniac/article/view/18274}
}
