Browsing by Author "Mendoza, Marcelo"

Now showing 1 - 3 of 3
  • No Thumbnail Available
    Item
    Boosting SpLSA for Text Classification
    (2017) Hurtado, Julio; Mendoza, Marcelo; Nanculef, Ricardo
    Text classification is a challenge in document labeling tasks such as spam filtering and sentiment analysis. Due to the descriptive richness of generative approaches such as probabilistic Latent Semantic Analysis (pLSA), documents are often modeled using these kind of strategies. Recently, a supervised extension of pLSA (spLSA [10]) has been proposed for human action recognition in the context of computer vision. In this paper we propose to extend spLSA to be used in text classification. We do this by introducing two extensions in spLSA: (a) Regularized spLSA, and (b) Label uncertainty in spLSA. We evaluate the proposal in spam filtering and sentiment analysis classification tasks. Experimental results show that spLSA outperforms pLSA in both tasks. In addition, our extensions favor fast convergence suggesting that the use of spLSA may reduce training time while achieving the same accuracy as more expensive methods such as sLDA or SVM.
  • No Thumbnail Available
    Item
    Enhancing commit message quality in software capstone projects with generative AI
    (2024) Neyem, Andres; Rios-Letelier, Agustin; Cespedes-Arancibia, Kevin; Alcocer, Juan Pablo Sandoval; Mendoza, Marcelo
    Software Capstone Projects provide valuable hands-on experience for students in software development, and creating effective commit messages is an essential, though often challenging, part of this process. These messages playa key role in managing repositories, facilitating collaboration, and offering insights into the project's progression for mentors and managers. However, creating high-quality commit messages can be challenging, especially for novice developers. We introduce LetsCommit, a tool designed to improve the traditional Git commit command line interface. The tool utilizes three state-of-the-art Large Language Models (LLMs): GPT-3.5, GPT-4, and LLaMa-2, to provide commit message suggestions to students. Results from a user experience survey showed high satisfaction, indicating strong potential for incorporating LetsCommit into future projects. Beyond its technical applications, LetsCommit possesses transformative potential in the field of education. The iterative learning process it supports, coupled with real-time insights, reinforces good software development practices and enhances the overall learning experience. These findings highlight LetsCommit's substantial impact on software engineering education, setting the stage for further advancements.
  • Thumbnail Image
    Item
    The Threat of Misinformation on Journalism’s Epistemology: Exploring the Gap between Journalist’s and Audience’s Expectations when Facing Fake Content
    (2024) Núñez Mussa, Enrique; Riquelme, Andrea; Valenzuela Leighton, Sebastián Andrés; Aldana, Valeria; Padilla, Fabián; Bassi, Renato; Campos, Sebastián; Providel, Eliana; Mendoza, Marcelo
    This study analyzes the discourse of reporters, editors and audiences in focus groups and in-depth interviews, examining the expectations on journalists when facing misinformation. While both groups agree that journalistic information is critical, how this expectation is met varies. On the one hand, the audience’s way of knowing involves diverse assessments regarding valuable information; also, they are dubious about journalists’ intentions. On the other hand, journalists exhibit a limited understanding of the audience’s informational needs and encounter practical challenges in rigorously fact-checking, affecting their authority in knowledge generation. The study proposes a discussion on acknowledging their complex epistemologies to benefit mutual understanding. Doing this can establish structural support for journalistic information, contributing to trust in journalism when challenged by sources spreading misinformation.