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
Publicações

Publicações por Álvaro Figueira

2016

Predicting Grades by Principal Component Analysis A Data Mining Approach to Learning Analyics

Autores
Figueira, A;

Publicação
2016 IEEE 16TH INTERNATIONAL CONFERENCE ON ADVANCED LEARNING TECHNOLOGIES (ICALT)

Abstract
In this paper we introduce three main features extracted from Moodle logs in order to be uses a possible means to predict future student grades. We discuss the statistical analysis on these features and show how they cannot be applied isolatedly to model our data. We then apply them as a whole and use principal component analysis to derive a decision tree based on the features. With derived tree we are able to predict grades in three intervals, namely to predict failures. Our proposed analysis methodology can be incorporated in an LMS and be used during a course. As the course unfolds, the system can to trigger alarms regarding possible failure situations.

2013

Creating Interopearable e-Portfolios for Different Educational Levels

Autores
Soares, S; Figueira, A;

Publicação
2013 IEEE GLOBAL ENGINEERING EDUCATION CONFERENCE (EDUCON)

Abstract
in this article we present a system capable of creating, managing and presenting digital portfolios. Our system innovates by using roles and states during its creation phase. This allows for high quality elements in the portfolio and promotes the students' reflection over them before full integration. The system also complies with the existing standards for e-portfolios. Moreover, it adds an extension to integrate previous created portfolios from different educational levels. In the article we show the need for such extension and describe how the system deals with integration of such diverse portfolios into a single one.

2016

Analyzing Social Media Discourse An Approach using Semi-supervised Learning

Autores
Figueira, A; Oliveira, L;

Publicação
PROCEEDINGS OF THE 12TH INTERNATIONAL CONFERENCE ON WEB INFORMATION SYSTEMS AND TECHNOLOGIES, VOL 2 (WEBIST)

Abstract
The ability to handle large amounts of unstructured information, to optimize strategic business opportunities, and to identify fundamental lessons among competitors through benchmarking, are essential skills of every business sector. Currently, there are dozens of social media analytics' applications aiming at providing organizations with informed decision making tools. However, these applications rely on providing quantitative information, rather than qualitative information that is relevant and intelligible for managers. In order to address these aspects, we propose a semi-supervised learning procedure that discovers and compiles information taken from online social media, organizing it in a scheme that can be strategically relevant. We illustrate our procedure using a case study where we collected and analysed the social media discourse of 43 organizations operating on the Higher Public Polytechnic Education Sector. During the analysis we created an "editorial model" that characterizes the posts in the area. We describe in detail the training and the execution of an ensemble of classifying algorithms. In this study we focus on the techniques used to increase the accuracy and stability of the classifiers.

2017

Communication and Resource Usage Analysis in Online Environments An Integrated Social Network Analysis and Data Mining Perspective

Autores
Figueira, A;

Publicação
PROCEEDINGS OF 2017 IEEE GLOBAL ENGINEERING EDUCATION CONFERENCE (EDUCON2017)

Abstract
Predicting whether a student will pass or fail is one of the most important actions to take while giving lectures. Usually, the experienced teacher is able to detect problematic situations at early stages. However, this is only true for classes up to a hundred students. For bigger ones, automatic methods are needed. In this paper, we present a predictive system based on three criteria retrieved and computed from the logs of the learning management system. We built fast frugal decision trees to help predict and prevent student failures, using data retrieved from their resource usage patterns. Evaluation of the decision system shows that the system's accuracy is very high both in train and test phases, surpassing logistic regression and CART. © 2017 IEEE.

2018

Human vs. Automatic Annotation Regarding the Task of Relevance Detection in Social Networks

Autores
Guimaraes, N; Miranda, F; Figueira, A;

Publicação
ADVANCES IN INTERNET, DATA & WEB TECHNOLOGIES

Abstract
The burst of social networks and the possibility of being continuously connected has provided a fast way for information diffusion. More specifically, real-time posting allowed news and events to be reported quicker through social networks than traditional news media. However, the massive data that is daily available makes newsworthy information a needle in a haystack. Therefore, our goal is to build models that can detect journalistic relevance automatically in social networks. In order to do it, it is essential to establish a ground truth with a large number of entries that can provide a suitable basis for the learning algorithms due to the difficulty inherent to the ambiguity and wide scope associated with the concept of relevance. In this paper, we propose and compare two different methodologies to annotate posts regarding their relevance: automatic and human annotation. Preliminary results show that supervised models trained with the automatic annotation methodology tend to perform better than using human annotation in a test dataset labeled by experts.

2017

Building a Semi-Supervised Dataset to Train Journalistic Relevance Detection Models

Autores
Guimaraes, N; Figueira, A;

Publicação
2017 IEEE 15TH INTL CONF ON DEPENDABLE, AUTONOMIC AND SECURE COMPUTING, 15TH INTL CONF ON PERVASIVE INTELLIGENCE AND COMPUTING, 3RD INTL CONF ON BIG DATA INTELLIGENCE AND COMPUTING AND CYBER SCIENCE AND TECHNOLOGY CONGRESS(DASC/PICOM/DATACOM/CYBERSCI

Abstract
Annotated data is one of the most important components for supervised learning tasks. To ensure the reliability of the models, this data is usually labeled by several human annotators through volunteering or using Crowdsourcing platforms. However, such approaches are unfeasible (regarding time and cost) in datasets with an enormous number of entries, which in the specific case of journalistic relevance detection in social media posts, is necessary due to the wide scope of topics that can be considered relevant. Therefore, with the goal of building a relevance detection model, we propose an architecture to build a large scale annotated dataset regarding the journalistic relevance of Twitter posts (i.e. tweets). This methodology is based on the predictability of the content in Twitter accounts. Next, we used the retrieved dataset and build relevance detection models, combining text, entities, and sentiment features. Finally, we validated the best model through a smaller manually annotated dataset with posts from Facebook and Twitter. The F1-measure achieved in the validation dataset was 63% which is still far from excellent. However, given the characteristics of the validation data, these results are encouraging since 1) our model is not affected by content from other social networks and 2) our validation dataset was restrained to a specific time interval and specific keywords (which can affect the performance of the model). © 2017 IEEE.

  • 5
  • 18