http://sedici.unlp.edu.ar:80/handle/10915/64817 Fri, 13 Nov 2026 16:21:56 GMT 2026-11-13T16:21:56Z http://sedici.unlp.edu.ar:80/handle/10915/64821 Objeto de conferencia XXIV Concurso Latinoamericano de Tesis de Maestría (CLTM-CLAI) - JAIIO 46 (Córdoba, 2017). In the current context of the Social Web, trust has emerged as a concept and mechanism to differentiate users of this Social Web and the content they generate. Much effort has been devoted to study trust predictors with the aim to provide some operational use of the concept. We propose in this work a new predictor for trust: knowledge obsolescence. We provide a characterization of the concept and a description of the relation between trust and knowledge obsolescence. We applied the concept to a generic recommender system. For this purpose, we have developed a software simulator that allow us to test trust and knowledge obsolescence networks in the recommender systems context. Interesting results were obtained. We found that recommender systems success is augmented. Moreover, we found an improvement in some cases for the coverage of potential recommendable items. We did not find statistical significant benefit on the quality of recommendations. Sun, 01 Jan 2017 00:00:00 GMT http://sedici.unlp.edu.ar:80/handle/10915/64821 2017-01-01T00:00:00Z In the current context of the Social Web, trust has emerged as a concept and mechanism to differentiate users of this Social Web and the content they generate. Much effort has been devoted to study trust predictors with the aim to provide some operational use of the concept. We propose in this work a new predictor for trust: knowledge obsolescence. We provide a characterization of the concept and a description of the relation between trust and knowledge obsolescence. We applied the concept to a generic recommender system. For this purpose, we have developed a software simulator that allow us to test trust and knowledge obsolescence networks in the recommender systems context. Interesting results were obtained. We found that recommender systems success is augmented. Moreover, we found an improvement in some cases for the coverage of potential recommendable items. We did not find statistical significant benefit on the quality of recommendations. http://sedici.unlp.edu.ar:80/handle/10915/64820 Objeto de conferencia XXIV Concurso Latinoamericano de Tesis de Maestría (CLTM-CLAI) - JAIIO 46 (Córdoba, 2017). The evolution of e-commerce and On-line Social Networks has contributed to the increase of the information available, making the task of analyzing the reviews manually almost impossible for the buying a product or service decisionmaking process. Due to the amount of information, the creation of automatic methods of knowledge extraction and data mining has become necessary. Currently, to facilitate the analysis of reviews some websites use filters such as votes by utility or by stars. However, the use of these filters is not a good practice because they may exclude reviews that have recently been submitted to the voting process, besides the possibility of the user overestimate or underestimate the review with attribution of stars. One possible solution is to filter the reviews based on their textual descriptions, author information and others measures. Sousa [1] proposed an approach, called TOP(X), to estimate the degree of importance of reviews using a Fuzzy System with three input variables: author reputation, extraction of tuples <feature, opinion word> and richness analyzer and an output variable: degree of importance of the review. Although the approach presented good results, some problems were pending of resolution and improvements, besides the possibility to change the computational model used. This work proposes adaptations in two input variables, namely: quantity of tuples and vocabulary richness and the building of new approaches using computational models based on Fuzzy Systems and Artificial Neural Networks (ANN). In addition, a comparison was made among the proposed approaches through statistical measures. Experiments performed in the hotel-domain showed that the approach using Fuzzy System obtained better results when detecting the most important reviews, without considering the semantic orientation of the comments. However, the approach using Multi-Layer Perceptron (MLP) Artificial Neural Networks obtained better results when is known the semantic orientation of the review. Sun, 01 Jan 2017 00:00:00 GMT http://sedici.unlp.edu.ar:80/handle/10915/64820 2017-01-01T00:00:00Z The evolution of e-commerce and On-line Social Networks has contributed to the increase of the information available, making the task of analyzing the reviews manually almost impossible for the buying a product or service decisionmaking process. Due to the amount of information, the creation of automatic methods of knowledge extraction and data mining has become necessary. Currently, to facilitate the analysis of reviews some websites use filters such as votes by utility or by stars. However, the use of these filters is not a good practice because they may exclude reviews that have recently been submitted to the voting process, besides the possibility of the user overestimate or underestimate the review with attribution of stars. One possible solution is to filter the reviews based on their textual descriptions, author information and others measures. Sousa [1] proposed an approach, called TOP(X), to estimate the degree of importance of reviews using a Fuzzy System with three input variables: author reputation, extraction of tuples <feature, opinion word> and richness analyzer and an output variable: degree of importance of the review. Although the approach presented good results, some problems were pending of resolution and improvements, besides the possibility to change the computational model used. This work proposes adaptations in two input variables, namely: quantity of tuples and vocabulary richness and the building of new approaches using computational models based on Fuzzy Systems and Artificial Neural Networks (ANN). In addition, a comparison was made among the proposed approaches through statistical measures. Experiments performed in the hotel-domain showed that the approach using Fuzzy System obtained better results when detecting the most important reviews, without considering the semantic orientation of the comments. However, the approach using Multi-Layer Perceptron (MLP) Artificial Neural Networks obtained better results when is known the semantic orientation of the review. http://sedici.unlp.edu.ar:80/handle/10915/64819 Objeto de conferencia XXIV Concurso Latinoamericano de Tesis de Maestría (CLTM-CLAI) - JAIIO 46 (Córdoba, 2017). In this master’s thesis Video Quality Assessment state of the art is reached. Different full reference (FR), reduced reference (RR) and no reference (NR) objective video quality estimation models, previously proposed by the research group, by the academic community or standardized by international organizations, are evaluated and analyzed. Their performance is compared by contrasting their results with ones obtained through subjective video quality evaluations. The ISDB-Tb standard of free-to-air Digital Television (DTV) is deepened, from the point of view of the correct reception and visualization of the DTV signal. Finally, this work contains specific contributions in the area of objective video quality assessment with application in DTV. In this thesis it is proposed and evaluated a new method that combines FR and NR objective models to perform the perceived video quality prediction in real time for the DTV signal. This new approach is based on modern video quality evaluation techniques under a DTV monitoring system with receiver nodes geographically distributed in the coverage area of a DTV station. Fri, 01 Sep 2017 00:00:00 GMT http://sedici.unlp.edu.ar:80/handle/10915/64819 2017-09-01T00:00:00Z In this master’s thesis Video Quality Assessment state of the art is reached. Different full reference (FR), reduced reference (RR) and no reference (NR) objective video quality estimation models, previously proposed by the research group, by the academic community or standardized by international organizations, are evaluated and analyzed. Their performance is compared by contrasting their results with ones obtained through subjective video quality evaluations. The ISDB-Tb standard of free-to-air Digital Television (DTV) is deepened, from the point of view of the correct reception and visualization of the DTV signal. Finally, this work contains specific contributions in the area of objective video quality assessment with application in DTV. In this thesis it is proposed and evaluated a new method that combines FR and NR objective models to perform the perceived video quality prediction in real time for the DTV signal. This new approach is based on modern video quality evaluation techniques under a DTV monitoring system with receiver nodes geographically distributed in the coverage area of a DTV station.