Ciencias Exactas y Ciencias de la Salud

Now showing 1 - 2 of 2

Social media to predict the 2024 mexican presidential election: a three model approach
(Instituto Tecnológico y de Estudios Superiores de Monterrey, 2024-12) Gutiérrez Valenzuela, Héctor Abel; Zareel, Mahdi; emipsanchez; Sánchez Ante, Gildardo; Biswal, Rajesh Roshan; School of Engineering and Sciences; Campus Monterrey; Brito, Kellyton
(Only 1 page) The appearance and rise of social media have evolved the way people interact with each other. From interpersonal communication to mass media production, social media applications have shifted the approach to how an individual or a complete corporation could generate and propagate a message. It was just a matter of time before this new way of reason- ing communication influenced political messages too. Ever since Obama´s 2008 and 2012 victories, the role social media could play in a presidential election was evident. More re- cently, the 2016 Cambridge Analytica scandal ultimately defined how influential the content people see on social media could be. Numerous research has emerged aiming to foresee these political movements based on online performance and many methods have been proposed. The definitive, most common pattern in these works is sentiment analysis in social media posts. The process is simple: detect how many people ’like’ a candidate´s online presence, and how many don´t, and this will likely represent the outcome of an election. However, this approach has sparked both criticism and unsatisfying results. The following work considers a contemporary approach to predicting elections with social media and collected polls. This strategy has succeeded in the case of various Latin American countries such as Argentina, Brazil, Colombia, and Mexico. However, we aim to identify potential flaws and improvements in the method to prove a concrete methodology can work outside a single election exercise, a repetitive cause for concern for multiple experts in the field. Results show that some replicated experiments do not successfully predict the result of the 2024 Mexican presidential election, as in 2018. However, we prove concrete method- ologies and models, like the multi-layer perceptron model (MLP) can successfully predict electoral results in more than one election. Moreover, we propose the least absolute shrink- age and selection operator (LASSO) to construct better and more descriptive predictors for electoral results. These two utilized implementations accurately predicted the winner of the 2024 election but remained short of the official performance of the winning candidate, Claudia Sheinbuam. In the case of the second and third place, both models merely missed the official result by 3 points.
Machine translation for suicide detection: validating spanish datasetsusing machine and deep learning models
(Instituto Tecnológico y de Estudios Superiores de Monterrey, 2024-11) Arenas Enciso, Francisco Ariel; Zareel, Mahdi; emipsanchez; García Ceja, Enrique Alejandro; Roshan Biswal, Rajesh; School of Engineering and Sciences; Sede EGADE Monterrey
Suicide is a complex health concern that affects not only individuals but society as a whole. The application of traditional strategies to prevent, assess, and treat this condition has proven inefficient in a modern world in which interactions are mainly made online. Thus, in recent years, multidisciplinary efforts have explored how computational techniques could be applied to automatically detect individuals who desire to end their lives on textual input. Such methodologies rely on two main technical approaches: text-based classification and deep learning. Further, these methods rely on datasets labeled with relevant information, often sourced from clinically-curated social media posts or healthcare records, and more recently, public social media data has proven especially valuable for this purpose. Nonetheless, research focused on the application of computational algorithms for detecting suicide or its ideation is still an emerging field of study. In particular, investigations on this topic have recently considered specific factors, like language or socio-cultural contexts, that affect the causality, rationality, and intentionality of an individual’s manifestation, to improve the assessment made on textual data. Consequently, problems like the lack of data in non-Anglo-Saxon contexts capable of exploiting computational techniques for detecting suicidal ideation are still a pending endeavor. Thus, this thesis addresses the limited availability of suicide ideation datasets in non-Anglo-Saxon contexts, particularly for Spanish, despite its global significance as a widely spoken language. The research hypothesizes that Machine- Translated Spanish datasets can yield comparable results (within a ±5% performance range) to English datasets when training machine learning and deep learning models for suicide ideation detection. To test this, multiple machine translation models were evaluated, and the two most optimal models were selected to translate an English dataset of social media posts into Spanish. The English and translated Spanish datasets were then processed through a binary classification task using SVM, Logistic Regression, CNN, and LSTM models. Results demonstrated that the translated Spanish datasets achieved scores in performance metrics close to the original English set across all classifiers, with limited variations in accuracy, precision, recall, F1-score, ROC AUC, and MCC metrics remaining within the hypothesized ±5% range. For example, the SVM classifier on the translated Spanish sets achieved an accuracy of 90%, closely matching the 91% achieved on the original English set. These findings confirm that machine-translated datasets can serve as effective resources for training ML and DL models for suicide ideation detection in Spanish, thereby supporting the viability of extending suicide detection models to non-English-speaking populations. This contribution provides a methodological foundation for expanding suicide prevention tools to diverse linguistic and cultural contexts, potentially benefiting health organizations and academic institutions interested in psychological computation.

Ciencias Exactas y Ciencias de la Salud

Browse

Filters

Settings

Sort By

Results per page

Search Results