New markov chain based methods for single and cross-domain sentiment classification

Nowadays communication is switching from a centralized scenario, where communication media like newspapers, radio, TV programs produce information and people are just consumers, to a completely different decentralized scenario, where everyone is potentially an information producer through the use of social networks, blogs, forums that allow a real-time worldwide information exchange. These new instruments, as a result of their widespread diffusion, have started playing an important socio-economic role. They are the most used communication media and, as a consequence, they constitute the main source of information enterprises, political parties and other organizations can rely on. Analyzing data stored in servers all over the world is feasible by means of Text Mining techniques like Sentiment Analysis, which aims to extract opinions from huge amount of unstructured texts. This could lead to determine, for instance, the user satisfaction degree about products, services, politicians and so on. In this context, this dissertation presents new Document Sentiment Classification methods based on the mathematical theory of Markov Chains. All these approaches bank on a Markov Chain based model, which is language independent and whose killing features are simplicity and generality, which make it interesting with respect to previous sophisticated techniques. Every discussed technique has been tested in both Single-Domain and Cross-Domain Sentiment Classification areas, comparing performance with those of other two previous works. The performed analysis shows that some of the examined algorithms produce results comparable with the best methods in literature, with reference to both single-domain and cross-domain tasks, in $2$-classes (i.e. positive and negative) Document Sentiment Classification. However, there is still room for improvement, because this work also shows the way to walk in order to enhance performance, that is, a good novel feature selection process would be enough to outperform the state of the art. Furthermore, since some of the proposed approaches show promising results in $2$-classes Single-Domain Sentiment Classification, another future work will regard validating these results also in tasks with more than $2$ classes.

Computational design of a new type of sandwich cross-section for a defined solution of a tree-like column produced by wire-and-arc additive manufacturing

When it comes to designing a structure, architects and engineers want to join forces in order to create and build the most beautiful and efficient building. From finding new shapes and forms to optimizing the stability and the resistance, there is a constant link to be made between both professions. In architecture, there has always been a particular interest in creating new shapes and types of a structure inspired by many different fields, one of them being nature itself. In engineering, the selection of optimum has always dictated the way of thinking and designing structures. This mindset led through studies to the current best practices in construction. However, both disciplines were limited by the traditional manufacturing constraints at a certain point. Over the last decades, much progress was made from a technological point of view, allowing to go beyond today's manufacturing constraints. With the emergence of Wire-and-Arc Additive Manufacturing (WAAM) combined with Algorithmic-Aided Design (AAD), architects and engineers are offered new opportunities to merge architectural beauty and structural efficiency. Both technologies allow for exploring and building unusual and complex structural shapes in addition to a reduction of costs and environmental impacts. Through this study, the author wants to make use of previously mentioned technologies and assess their potential, first to design an aesthetically appreciated tree-like column with the idea of secondly proposing a new type of standardized and optimized sandwich cross-section to the construction industry. Parametric algorithms to model the dendriform column and the new sandwich cross-section are developed and presented in detail. A catalog draft of the latter and methods to establish it are then proposed and discussed. Finally, the buckling behavior of this latter is assessed considering standard steel and WAAM material properties.

Tree regularized neural networks for key point analysis

This thesis contributes to the ArgMining 2021 shared task on Key Point Analysis. Key Point Analysis entails extracting and calculating the prevalence of a concise list of the most prominent talking points, from an input corpus. These talking points are usually referred to as key points. Key point analysis is divided into two subtasks: Key Point Matching, which involves assigning a matching score to each key point/argument pair, and Key Point Generation, which consists of the generation of key points. The task of Key Point Matching was approached using different models: a pretrained Sentence Transformers model and a tree-constrained Graph Neural Network were tested. The best model was the fine-tuned Sentence Transformers, which achieved a mean Average Precision score of 0.75, ranking 12 compared to other participating teams. The model was then used for the subtask of Key Point Generation using the extractive method in the selection of key point candidates and the model developed for the previous subtask to evaluate them.