Instituto Politécnico Nacional

About: Instituto Politécnico Nacional is a education organization based out in Mexico City, Mexico. It is known for research contribution in the topics: Population & Context (language use). The organization has 43351 authors who have published 63315 publications receiving 938532 citations. The organization is also known as: Instituto Politécnico Nacional & Instituto Politecnico Nacional.

Open source software projects as virtual organisations: competency rallying for software development

Abstract: Contributes to the identification and testing of factors important for the success of open source software (OSS) projects. We present an analysis of OSS communities as virtual organisations, and apply Katzy and Crowston's (2000) competency rallying (CR) theory to the case of OSS development projects. CR theory suggests that project participants must develop necessary competencies, identify and understand market opportunities, marshal competencies to meet the opportunity and manage a short-term co-operative process. Using data collected from 7477 OSS projects hosted by the SourceForge system, we formulate and test a set of specific hypotheses derived from CR theory. The empirical data analysis supports the majority of these hypotheses, suggesting that CR theory provides a useful lens for studying OSS projects.

Multimodal sentiment analysis using hierarchical fusion with context modeling

Abstract: Multimodal sentiment analysis is a very actively growing field of research. A promising area of opportunity in this field is to improve the multimodal fusion mechanism. We present a novel feature fusion strategy that proceeds in a hierarchical fashion, first fusing the modalities two in two and only then fusing all three modalities. On multimodal sentiment analysis of individual utterances, our strategy outperforms conventional concatenation of features by 1%, which amounts to 5% reduction in error rate. On utterance-level multimodal sentiment analysis of multi-utterance video clips, for which current state-of-the-art techniques incorporate contextual information from other utterances of the same clip, our hierarchical fusion gives up to 2.4% (almost 10% error rate reduction) over currently used concatenation. The implementation of our method is publicly available in the form of open-source code.