The Internet has revolutionized the way users share and acquire knowledge. As important and popular Web-based applications, online discussion forums provide interactive platforms for users to exchange information and report problems. With the rapid growth of social networks and an ever increasing number of Internet users, online forums have accumulated a huge amount of valuable user-generated data and have accordingly become a major information source for business intelligence. This study focuses specifically on product defects, which are one of the central concerns of manufacturing companies and service providers, and proposes a machine learning method to automatically detect product defects in the context of online forums. To complement the detection of product defects , we also present a product feature extraction method to summarize defect threads and a thread ranking method to search for troubleshooting solutions. To this end, we collected different data sets to test these methods experimentally and the results of the tests show that our methods are very promising: in fact, in most cases, they outperformed the current state-of-the-art methods. / Ph. D.

Product defects concern various groups of people, such as customers, manufacturers, government officials, etc. Thus, defect-related knowledge and information are essential. In keeping with the growth of social media, online forums, and Internet commerce, people post a vast amount of feedback on products, which forms a good source for the automatic acquisition of knowledge about defects. However, considering the vast volume of online reviews, how to automatically identify critical product defects and summarize the related information from the huge number of user reviews is challenging, even when we target only the negative reviews. As a kind of opinion mining research, existing defect discovery methods mainly focus on how to classify the type of product issues, which is not enough for users. People expect to see defect information in multiple facets, such as product model, component, and symptom, which are necessary to understand the defects and quantify their influence. In addition, people are eager to seek problem resolutions once they spot defects. These challenges cannot be solved by existing aspect-oriented opinion mining models, which seldom consider the defect entities mentioned above. Furthermore, users also want to better capture the semantics of review text, and to summarize product defects more accurately in the form of natural language sentences. However, existing text summarization models including neural networks can hardly generalize to user review summarization due to the lack of labeled data. In this research, we explore topic models and neural network models for product defect discovery and summarization from user reviews. Firstly, a generative Probabilistic Defect Model (PDM) is proposed, which models the generation process of user reviews from key defect entities including product Model, Component, Symptom, and Incident Date. Using the joint topics in these aspects, which are produced by PDM, people can discover defects which are represented by those entities. Secondly, we devise a Product Defect Latent Dirichlet Allocation (PDLDA) model, which describes how negative reviews are generated from defect elements like Component, Symptom, and Resolution. The interdependency between these entities is modeled by PDLDA as well. PDLDA answers not only what the defects look like, but also how to address them using the crowd wisdom hidden in user reviews. Finally, the problem of how to summarize user reviews more accurately, and better capture the semantics in them, is studied using deep neural networks, especially Hierarchical Encoder-Decoder Models. For each of the research topics, comprehensive evaluations are conducted to justify the effectiveness and accuracy of the proposed models, on heterogeneous datasets. Further, on the theoretical side, this research contributes to the research stream on product defect discovery, opinion mining, probabilistic graphical models, and deep neural network models. Regarding impact, these techniques will benefit related users such as customers, manufacturers, and government officials. / Ph. D. / Product defects concern various groups of people, such as customers, manufacturers, and government officials. Thus, defect-related knowledge and information are essential. In keeping with the growth of social media, online forums, and Internet commerce, people post a vast amount of feedback on products, which forms a good source for the automatic acquisition of knowledge about defects. However, considering the vast volume of online reviews, how to automatically identify critical product defects and summarize the related information from the huge number of user reviews is challenging, even when we target only the negative reviews. People expect to see defect information in multiple facets, such as product model, component, and symptom, which are necessary to understand the defects and quantify their influence. In addition, people are eager to seek problem resolutions once they spot defects. Furthermore, users also want to better summarize product defects more accurately in the form of natural language sentences. These requirements cannot be satisfied by existing methods, which seldom consider the defect entities mentioned above, or hardly generalize to user review summarization. In this research, we develop novel Machine Learning (ML) algorithms for product defect discovery and summarization. Firstly, we study how to identify product defects and their related attributes, such as Product Model, Component, Symptom, and Incident Date. Secondly, we devise a novel algorithm, which can discover product defects and the related Component, Symptom, and Resolution, from online user reviews. This method tells not only what the defects look like, but also how to address them using the crowd wisdom hidden in user reviews. Finally, we address the problem of how to summarize user reviews in the form of natural language sentences using a paraphrase-style method. On the theoretical side, this research contributes to multiple research areas in Natural Language Processing (NLP), Information Retrieval (IR), and Machine Learning. Regarding impact, these techniques will benefit related users such as customers, manufacturers, and government officials.

This thesis deals with the topic of liability for damage caused by a defect in a product, i.e. liability of a producer (but also of another entity, such as the supplier or importer) for damage caused by the defective product to the health or property of the user (consumer) or other third persons. The primary area of this issue that the thesis has examined is the legal regulation in the UK (liability for damage caused by a defect in a product is in the UK usually expressed as "Product liability"). The main reason why I have chosen to describe the British legal regulation is my study experience in the UK at Northumbria University, where I studied within the program Erasmus+. In the UK, I had the opportunity to find all the resources, experience and incentives necessary in order to analyze the topic of Product liability and therefore, to write this thesis. The aim of this thesis is not only the description of the British Product liability, but also its comparison with the Czech regulation. This thesis then draws a clear conclusion that Product liability in the UK is as compared to the Czech Republic an institute much more frequently used and British regulation is compared to the Czech one more sophisticated and detailed. On the other hand, for the British consumers the British regulation may be, due...

This diploma thesis quite thoroughly deals with - at present a very topical - theme "liability for damage caused by a defective product"; thus, with an obligation to compensate for the damage caused by the defective product to its user (or third party), generally imposed on the person who is designated as the "producer" of the product, originally based on the Council Directive of 25 July 1985 on the approximation of the laws, regulations and administrative provisions of the Member States concerning liability for defective products (85/374/EEC) (hereinafter 'Directive 85/374/EEC'). However, this work is not limited only to the (thorough) description of the currently valid and effective Czech implementing legislation. The thesis also compares the Czech legislation with the French implementing regulation, which is of a significantly higher legislative quality and much more faithful to its Union model. In fact, it was specifically France which shaped the final form of this responsibility regime, since it was the French transposition, and the French decision-making (judicial) practice, which was most often the subject of the Court of Justice's, as it ruled on the interpretation of the individual provisions and principles in the text of the previously mentioned directive contained. Nevertheless, France,...

Alors que le contentieux des produits de santé n'a jamais été aussi fourni, l'application du régime spécial de responsabilité du fait des produits défectueux issu de la directive européenne du 25 juillet 1985, entraîne l'émergence d'un certain nombre d'incertitudes qui affectent directement le sort des demandes en réparation. Les incertitudes matérielles ont, pour la plupart reçu un traitement efficace par l'action conjuguée de la jurisprudence et du législateur. Si les outils juridiques traditionnels, tels que les présomptions ou la causalité alternative, ont permis de résoudre une partie non négligeable de ces incertitudes, les juges se sont également attachés à développer des outils nouveaux comme la balance bénéfice/risque ou encore la répartition de l'obligation à la dette selon les parts de marché. Cependant, si le développement de ces outils juridiques, plus adaptés aux spécificités des produits de santé, a permis d'apporter une solution efficace aux incertitudes matérielles, le traitement de l'incertitude scientifique, fondé sur les présomptions du fait de l'homme, n'apporte, toujours pas, de solutions satisfaisantes. L'étude du traitement des incertitudes dans le contentieux des produits de santé défectueux permet d'apprécier les acquis mais également les limites atteintes par l'utilisation de certains outils mis à la disposition des juges et qui se révèlent parfois inadaptés. L'intervention du législateur et la prise en compte des spécificités des produits de santé, permettraient de développer un système d'indemnisation adapté qui interviendrait de façon subsidiaire en cas d'échec de la voie contentieuse. / At a time when healthcare-product litigation is attaining record heights, the implementation into French law of the special liability regime for defective products, which derives from the European Council Directive of 25 July 1985, has led to the emergence of several grey areas of uncertainty which have a direct impact on the outcome of claims for compensation. Areas of material uncertainty have, for the most part, been effectively dealt with through the combined application of case law and the intervention of the legislator. While classic legal tools such as presumption and alternative causality provide a means to resolve a non-negligible part of these uncertainties, judges have also endeavoured to develop new tools, such as risk/utility test and market-share liability. Still, although the development of these legal tools - better suited as they are to the specific features of healthcare products - provide an effective solution to resolving areas of material uncertainty, the treatment of scientific uncertainty, which is based on presumptions of fact, does not always provide satisfactory solutions. The study of the legal treatment of uncertainty in healthcare-product litigation provides a means to assess the benefits but also the limitations of certain tools that are now available to judges but which at times prove inadequate. Intervention on the part of the legislator, while at the same time taking into account the specific features of healthcare products, could lead to the development of a suitable compensation system that could afford relief when litigation fails.