The increasing interest in how stance is expressed specifically in academic writing in English has generated extensive research in the past decades. Focusing on the grammatical marking of stance, this comparative study investigates the use of stance adverbials by native (L1) and nonnative (L2) speakers of English in a corpus of student academic writing. The aim is to examine the most distinctive differences and similarities in the use of adverbial stance markers by each student group. The material comes from the British Academic Writing in English (BAWE) corpus, a collection of proficient writing by English L1 and L2 students from different firstlanguage backgrounds. Using quantitative methods and a semantically-based classification, the forms and types of stance adverbials most frequently used by the two student groups are identified and compared. The findings indicate that L1 students employ more adverbial stance markers overall, which contradicts results from previous research, but that both L1 and L2 students make use predominantly of a limited number of stance adverbials. The analysis of the most frequently used adverbials indicates underuse (e.g. perhaps) and overuse (e.g. kind of, mainly ) of specific markers on the part of the L2 group. The results partially invalidate the hypothesis tested that L2 students both rely on a narrower range of stance adverbials and employ them more frequently than L1 students.

Detecção de posicionamento é a tarefa de automaticamente identificar se o autor de um texto é favorável, contrário, ou nem favorável e nem contrário a uma dada proposição ou alvo. Com o amplo uso do Twitter como plataforma para expressar opiniões e posicionamentos, a análise automatizada deste conteúdo torna-se de grande valia para empresas, organizações e figuras públicas. Em geral, os trabalhos que exploram tal tarefa adotam abordagens supervisionadas ou semi-supervisionadas. O presente trabalho propõe e avalia um processo não supervisionado de detecção de posicionamento em textos de tweets que tem como entrada apenas o alvo e um conjunto de tweets a rotular e é baseado em uma abordagem híbrida composta por 2 etapas: a) rotulação automática de tweets baseada em um conjunto de heurísticas e b) classificação complementar baseada em aprendizado supervisionado de máquina. A proposta tem êxito quando aplicada a figuras públicas, superando o estado-da-arte. Além disso, são avaliadas alternativas no intuito de melhorar seu desempenho quando aplicada a outros domínios, revelando a possibilidade de se empregar estratégias tais como o uso de alvos e perfis semente dependendo das características de cada domínio. / Stance Detection is the task of automatically identifying if the author of a text is in favor of the given target, against the given target, or whether neither inference is likely. With the wide use of Twitter as a platform to express opinions and stances, the automatic analysis of this content becomes of high regard for companies, organizations and public figures. In general, works that explore such task adopt supervised or semi-supervised approaches. The present work proposes and evaluates a non-supervised process to detect stance in texts of tweets that has as entry only the target and a set of tweets to classify and is based on a hybrid approach composed by 2 stages: a) automatic labelling of tweets based on a set of heuristics and b) complementary classification based on supervised machine learning. The proposal succeeds when applied to public figures, overcoming the state-of-the-art. Beyond that, some alternatives are evaluated with the intention of increasing the performance when applied to other domains, revealing the possibility of use of strategies such as using seed targets and profiles depending on each domain characteristics.

Detecção de posicionamento é a tarefa de automaticamente identificar se o autor de um texto é favorável, contrário, ou nem favorável e nem contrário a uma dada proposição ou alvo. Com o amplo uso do Twitter como plataforma para expressar opiniões e posicionamentos, a análise automatizada deste conteúdo torna-se de grande valia para empresas, organizações e figuras públicas. Em geral, os trabalhos que exploram tal tarefa adotam abordagens supervisionadas ou semi-supervisionadas. O presente trabalho propõe e avalia um processo não supervisionado de detecção de posicionamento em textos de tweets que tem como entrada apenas o alvo e um conjunto de tweets a rotular e é baseado em uma abordagem híbrida composta por 2 etapas: a) rotulação automática de tweets baseada em um conjunto de heurísticas e b) classificação complementar baseada em aprendizado supervisionado de máquina. A proposta tem êxito quando aplicada a figuras públicas, superando o estado-da-arte. Além disso, são avaliadas alternativas no intuito de melhorar seu desempenho quando aplicada a outros domínios, revelando a possibilidade de se empregar estratégias tais como o uso de alvos e perfis semente dependendo das características de cada domínio. / Stance Detection is the task of automatically identifying if the author of a text is in favor of the given target, against the given target, or whether neither inference is likely. With the wide use of Twitter as a platform to express opinions and stances, the automatic analysis of this content becomes of high regard for companies, organizations and public figures. In general, works that explore such task adopt supervised or semi-supervised approaches. The present work proposes and evaluates a non-supervised process to detect stance in texts of tweets that has as entry only the target and a set of tweets to classify and is based on a hybrid approach composed by 2 stages: a) automatic labelling of tweets based on a set of heuristics and b) complementary classification based on supervised machine learning. The proposal succeeds when applied to public figures, overcoming the state-of-the-art. Beyond that, some alternatives are evaluated with the intention of increasing the performance when applied to other domains, revealing the possibility of use of strategies such as using seed targets and profiles depending on each domain characteristics.

A dissertação pretende permitir ao leitor simular a forma de pensar de Daniel Dennett, e perpassa toda sua filosofia, com ênfase em seu tratamento de o que são padrões, o algoritmo evolutivo, intuition pumps, consciência, e seu uso dos conceitos de illata, abstracta, semântica e sintaxe para compreender a natureza, a biologia e a mente humana. O trabalho reapresenta, sob nova luz, grande parte das ideias mais importantes de Dennett, e procura fazer a engenharia reversa de o que o levou a pensar de determinadas maneiras, guiando o leitor através de caminhos similares, procurando fomentar um aprendizado ativo de uma forma de pensar, acima e além de uma exposição dos resultados obtidos ao longo de décadas desse pensamento no próprio Dennett / This dissertation intends to provide the reader with an inner simulation of Daniel Dennetts form of reasoning, spreading over his whole philosophy, emphasizing his treatment of patterns, the evolutionary algorithm, consciousness, and his use of illata, abstracta, semantic, and synthax, to carve nature at its joints, especially biology and the human mind. It recasts, in a new light, great part of his most important ideas, and reverse engineers what made him think in particular ways, walking the reader through similar pathways, fostering an active learning of a thinking style, above and beyond a mere exposition of the results obtained by this thinking style over the years

Submitted by Luciana Ferreira (lucgeral@gmail.com) on 2017-11-09T14:22:53Z No. of bitstreams: 2 Tese - Leonardo Venicius Parreira Proto - 2017.pdf: 4628771 bytes, checksum: a915c6bcf6150fa8dd36c679f97a4b4a (MD5) license_rdf: 0 bytes, checksum: d41d8cd98f00b204e9800998ecf8427e (MD5) / Approved for entry into archive by Luciana Ferreira (lucgeral@gmail.com) on 2017-11-09T14:23:44Z (GMT) No. of bitstreams: 2 Tese - Leonardo Venicius Parreira Proto - 2017.pdf: 4628771 bytes, checksum: a915c6bcf6150fa8dd36c679f97a4b4a (MD5) license_rdf: 0 bytes, checksum: d41d8cd98f00b204e9800998ecf8427e (MD5) / Made available in DSpace on 2017-11-09T14:23:44Z (GMT). No. of bitstreams: 2 Tese - Leonardo Venicius Parreira Proto - 2017.pdf: 4628771 bytes, checksum: a915c6bcf6150fa8dd36c679f97a4b4a (MD5) license_rdf: 0 bytes, checksum: d41d8cd98f00b204e9800998ecf8427e (MD5) Previous issue date: 2017-10-05 / Fundação de Amparo à Pesquisa do Estado de Goiás - FAPEG / In this doctoral dissertation, we research the intellectual stance of Florestan Fernandes and we also seek to flesh out the reasoning that generated such a position and why he assumes this stance in the national and intellectual scenario. His intellectual perspective approximated the political standings influenced by Leninism and Gramscianism, according to his choice of militancy through the institutionalized political path, in his performance in the political party and his involvement with parliamentary activity. The party's choice as an instrument of insertion in national public life was associated with his conception of Marxism and the defense of what is called proletarian socialism. In methodological terms, we analyzed his bibliography which has connections with Marxism, the Workers' Party (PT), Socialism, class struggles and bourgeois democracy, as well as published interviews, printed and on videos, in order to verify his thoughts on these issues. In this regard, as it can be verified in this work, we rely on the theoretical framework of Marxism to analyze his intellectual production according to his social class and sense of belonging, in this case the intellectuality, and from the notion of social sphere and the intellectual sphere. We discuss his standing and stance in the face of Brazilian reality and what he considered as Marxism and the forms of working class action in favor of the constitution of proletarian socialism. For us, there is an approximation of the ideological contributions of Leninism-Gramscianism in his conception of Marxism, which we conceive as the deformation of Marxism in terms of the false systematized consciousness of reality, by defending, in his stances, institutionalized organizations such as the party and the trade union, understood by him as instruments of struggle necessary for the working class to overcome capitalism and extinguish bourgeois domination. His intellectual perspective is determined by his Leninist and Gramscian political formation which allows him to act in bureaucratic organizations expressing, thus, a political positioning derived from his connections with the university and the political party. Therefore, the need of getting himself involved with the burning issues of national debate and the class struggles made him defend institutionalized instruments of struggle, generating an ambiguous outlook assumed throughout the development of his trajectory of action in the scope of the university and of the political party, which confirms his distancing from authentic Marxism and its revolutionary character. / Nesta tese pesquisamos a postura intelectual de Florestan Fernandes e buscamos problematizar as determinações que geraram tal postura intelectual e os motivos pelos quais assume esta postura no cenário nacional e intelectual. Sua postura intelectual aproximava-se de posicionamentos políticos influenciados pelo leninismo e gramscianismo, conforme sua opção de militância pela via política institucionalizada, em sua atuação no partido político e envolvimento com a atividade parlamentar. A escolha do partido como instrumento de inserção na vida pública nacional estava associado à sua concepção de marxismo e à defesa do que denominou de socialismo proletário. Em termos metodológicos, analisamos sua bibliografia que versava a respeito do marxismo, do Partido dos Trabalhadores (PT), do socialismo, da luta de classes, da democracia burguesa, bem como entrevistas publicadas impressas e em vídeo, com intuito de verificarmos suas ideias e posicionamentos acerca destas questões. Para isto, conforme pode ser verificado neste trabalho, nos apoiamos no referencial teórico do marxismo, e analisamos sua atividade intelectual de acordo com a classe social de pertencimento, no caso, a intelectualidade e a partir da noção de esfera social, da esfera intelectual, discutimos sua posição e posicionamento diante da realidade brasileira e daquilo que considerava como marxismo e as formas de atuação da classe trabalhadora em prol da constituição do socialismo proletário. Para nós, há em sua concepção de marxismo uma aproximação de aportes ideológicos do leninismo-gramscianismo, o que concebemos como deformação do marxismo em termos da falsa consciência sistematizada da realidade, ao defender em seus posicionamentos organizações institucionalizadas, como o partido e o sindicato, compreendidos por ele como instrumentos de luta necessários para a classe trabalhadora superar o capitalismo e extinguir a dominação burguesa. Sua postura intelectual é determinada pela sua formação política leninista e gramsciana, que o permite atuar em organizações burocráticas, expressando assim um posicionamento político oriundo de suas ligações com a universidade e o partido político. Portanto, a necessidade de se envolver com questões candentes do debate nacional e da luta de classes o fez defender instrumentos institucionalizados de luta, gerando uma postura intelectual ambígua, assumida ao longo do desenvolvimento de sua trajetória de atuação no âmbito da universidade e do partido político, confirmando seu distanciamento do marxismo autêntico e do seu caráter revolucionário.

This study is a corpus-based comparison between student essays written in the subject areas of English linguistics and literature at undergraduate level. They are 200 Bachelor degree theses submitted at a variety of university departments (such as English, Language and Literature, Humanities, Social and Intercultural Studies) in Sweden. The comparison concerns frequencies of core modal verbs and how often they occur together with the I, we and it subject pronouns and in the structures this/the [essay, study, project, thesis] when students attempt to communicate their personal claims. Quantitative and qualitative analyses of the essays show few similarities in the ways that core modal verbs appear in both disciplines. The results indicate mainly distinct differences, especially in relation to clusters and variation of performative verbs. Specific patterns in the ways that students use core modal verbs as hedges have also been identified. / <p>Engelska</p>

Abstract This thesis reports on an empirical study of the forms and functions of two interrelated syntactic constructions, tag questions and negative yes/no interrogatives, in naturally occurring American English conversations. More specifically, the thesis focuses on examining the ways in which these interrogative constructions are involved in the intersubjective and interactional construction of stance. This involves describing the linguistic and interactional practices through which speakers index and negotiate their evaluative, affective or epistemic position or point of view towards some matter in the local context. The data used in the study comprise naturally occurring face-to-face and telephone interactions the majority of which take place between family and friends. The data are drawn from the first three published parts of the Santa Barbara Corpus of Spoken American English.The study is based on the methodological and theoretical principles of interactional linguistics and conversation analysis. The first part of the study provides an examination of the linguistic and grammatical patterning of the chosen constructions in a database of naturally occurring interactions in English. This serves first of all as a study of the general linguistic patterning of utterances with negation or reversed word order in interaction. At the same time, however, the grammatical and semantic categories of person, verb type and tense are employed for establishing the high frequency of linguistic and semantic material that index the current speaker's affective, evaluative and/or epistemic position towards the issue at hand. The second part of the study expands the focus from individual utterances to the surrounding interactional context in which the interrogative constructions are located, and makes use of the conversation analytic methodology. I examine how discourse participants use negative yes/no interrogatives and tag questions as a resource for carrying out different actions such as requesting for confirmation, challenging, disagreeing and assessing, and the ways in which interrogative speakers convey their epistemic, affective or evaluative stances in so doing. In this section of the study the research proceeds through detailed analyses of interaction, and an examination of those sequential environments in which the interrogative constructions are found.

The Ottawalk-Speed (OWS) orthosis prevents knee collapse in stumble situations. The purpose of this study was to develop a virtual stumble perturbation to measure OWS response to a knee collapse when walking. A new split speed perturbation was developed for the CAREN virtual reality system. This perturbation induced a stumble with increased knee flexion for five able-bodied participants, with either a hopping or stopping recovery strategy. Three knee-ankle-foot orthosis users were subjected to five stumble trials while wearing the OWS. OWS participants used a straight-legged recovery strategy, and extended the knee through recovery weight acceptance. Therefore, the split speed perturbation was not appropriate to measure OWS response to a stumble since knee collapse did not occur. The OWS allowed free knee motion during gait. Further study is required to measure OWS response during a stumble with a knee collapse event.

Computational approaches to opinion mining have mostly focused on polarity detection of product reviews by classifying the given text as positive, negative or neutral. While, there is less effort in the direction of socio-political opinion mining to determine favorability towards given targets of interest, particularly for social media data like news comments and tweets. In this research, we explore the task of automatically determining from the text whether the author of the text is in favor of, against, or neutral towards a proposition or target. The target may be a person, an organization, a government policy, a movement, a product, etc. Moreover, we are interested in detecting the reasons behind authors’ positions. This thesis is organized into three main parts: the first part on Twitter stance detection and interaction of stance and sentiment labels, the second part on detecting stance and the reasons behind it in online news comments, and the third part on multi-target stance classification. One may express favor (or disfavor) towards a target by using positive or negative language. Here, for the first time, we present a dataset of tweets annotated for whether the tweeter is in favor of or against pre-chosen targets, as well as for sentiment. These targets may or may not be referred to in the tweets, and they may or may not be the target of opinion in the tweets. We develop a simple stance detection system that outperforms all 19 teams that participated in a recent shared task competition on the same dataset (SemEval-2016 Task #6). Additionally, access to both stance and sentiment annotations allows us to conduct several experiments to tease out their interactions. Next, we proposed a novel framework for joint learning of stance and reasons behind it. This framework relies on topic modeling. Unlike other machine learning approaches for argument tagging which often require a large set of labeled data, our approach is minimally supervised. The extracted arguments are subsequently employed for stance classification. Furthermore, we create and make available the first dataset of online news comments manually annotated for stance and arguments. Experiments on this dataset demonstrate the benefits of using topic modeling, particularly Non-Negative Matrix Factorization, for argument detection. Previous models for stance classification often treat each target independently, ignoring the potential (sometimes very strong) dependency that could exist among targets. However, in many applications, there exist natural dependencies among targets. In this research, we relieve such independence assumptions in order to jointly model the stance expressed towards multiple targets. We present a new dataset that we built for this task and make it publicly available. Next, we show that an attention-based encoder-decoder framework is very effective for this problem, outperforming several alternatives that jointly learn dependent subjectivity through cascading classification or multi-task learning.

[ES] En esta tesis abordamos el problema de la detección de las opiniones (stance detection, SD) en las redes sociales, centrándose en los debates políticos polarizados en Twitter. La SD consiste en determinar automáticamente si el autor de una publicación está a favor o en contra de un objetivo de interés, o si no se puede inferir la opinión. Nos ocupamos de temas políticos como las elecciones políticas y los referendos y, como resultado, los objetivos son tanto personas como referendos. También exploramos las comunicaciones que tienen lugar en estos debates polarizados, arrojando luz sobre las dinámicas de comunicación entre personas que tienen opiniones en acuerdo o en conflicto, enfocándonos en particular en la observación del cambio de opiniones (opinion shifting). Proponemos modelos de aprendizaje automático para la SD como si fuera un problema de clasificación binaria. Exploramos características basadas en el contenido del texto del tweet, además usamos características basadas en información contextual que no emerge directamente del texto. Utilizando el corpus de benchmark propuesto para la tarea compartida sobre la SD realizado para SemEval 2016, exploramos la contribución que el estudio de las relaciones entre el objetivo de interés y las otras entidades involucradas en el debate proporciona a la SD. Al participar en la tarea ``Stance and Gender Detection in Tweets on Catalan Independence'' organizado para IberEval 2017, hemos propuesto otras características textuales y contextuales para la SD en tweets en español y en catalán. Explorando la SD desde una perspectiva multilingüe, hemos creado un corpus de tweets en francés y uno en italiano. La extensión multilingüe de nuestro modelo (multiTACOS) muestra que la SD está influenciada más por los diferentes estilos utilizados por los usuarios para comunicar la opinión sobre objetivos de diferentes tipos (personas o referendos) en lugar del idioma utilizado. Con el objetivo de recuperar información contextual sobre la red social de los usuarios de Twitter (generalmente las tareas compartidas solo consisten en el contenido del tweet, dejando de lado la información sobre el usuario), hemos creado otros dos conjuntos de datos, uno en inglés y uno en italiano, respectivamente, sobre el Brexit (TW-BREXIT) y sobre el referéndum constitucional italiano (ConRef-STANCE-ita). En ambos casos de estudio, mostramos que los usuarios tienden a agruparse en grupos con ideas similares. Por este motivo, el modelo que explota el conocimiento de la comunidad social a la que el autor del tweet pertenece, supera los resultados obtenidos utilizando solo las funciones basadas en el contenido de la publicación. Además, la evidencia muestra que los usuarios utilizan diferentes tipos de comunicación según el nivel de acuerdo con la opinión del interlocutor, por ejemplo, las relaciones de amistad, los retweets y las citas (quote) son más comunes entre los usuarios relacionados, mientras que las respuestas (replies) se utilizan a menudo para interactuar con usuarios que tienen diferentes posiciones. Al abordar la SD desde una perspectiva diacrónica, también observamos tanto el cambio de opinión como la mitigación del debate hacia posiciones neutrales después del resultado de la votación. Además, hemos observado que tener contacto con una variedad más amplia de opiniones puede influir en la propensión a cambiar de opinión. Finalmente, mostramos que las características basadas en una representación gráfica de un dominio de interés no se limitan a la SD, sino que se puede aplicar a diferentes escenarios. Al proponer otra tarea de clasificación que realiza la identificación del talento en el deporte, especialmente en el estudio de caso del tenis de mesa, mostramos que las métricas de redes basadas en la centralidad son una señal fuerte para el talento y pueden usarse para entrenar un modelo de algoritmo de aprendizaje automático para enfrentar esta / [CAT] En aquesta tesi doctoral abordem el problema de la detecció de posició (stance detection, SD) en els mitjans de comunicació social, especialment centrat en els debats polítics polaritzats a Twitter. La SD consisteix a determinar automàticament si l'autor d'una publicació està a favor o en contra d'un objectiu o tema d'interès, o si l'opinió envers d'aquest objectiu o tema determinat no es pot inferir. Ens ocupem de temes polítics com ara esdeveniments electorals i, en conseqüència, els temes d'interès són, en concret, la SD en vers dirigents polítics i referèndums. També explorem les comunicacions que es duen a terme en aquests debats polaritzats, que posen de manifest la dinàmica de les comunicacions entre les persones que tenen opinions concordants o contrastades, especialment centrant-nos en l'observació del canvi de les opinions. Proposem models d'aprenentatge automàtic per abordar la SD com un problema de classificació. Explorem les funcions basades en el contingut textual del tweet, però també les funcions basades en la informació contextual que no afloren directament del text. Utilitzem el conjunt de dades de referència en anglès proposat per a les tasques compartides sobre SD celebrades a SemEval 2016, per explorar la contribució a la SD d'investigar les relacions entre l'objectiu d'interès i les altres entitats implicades en el debat. En la participació a la tasca compartida de ``Stance and Gender Detection in Tweets on Catalan Independence'' celebrada a IberEval 2017, es van proposar altres trets textuals i contextuals per detectar la posició dels autors dels tweets, escrits en espanyol i en català, envers la independència de Catalunya. L'extensió multilingüe del model de SD (multiTACOS) mostra que la SD es veu afectada pels diferents estils que utilitzen els usuaris per comunicar la posició envers objectius de diferents tipus (persones o referèndum) més que la llengua utilitzada. Amb l'objectiu de recuperar informació contextual sobre la xarxa social dels usuaris de Twitter (les tasques compartides solen publicar només el contingut del tweet i deixen de banda, en canvi, la informació sobre la persona que escriu el tweet), vam crear dos conjunts més de dades, un en anglès i un en italià, el corpus Brexit (TW-BREXIT) i el corpus del referèndum constitucional italià (ConRef-STANCE-ita) respectivament. En els dos casos, demostrem que els usuaris tendeixen a agrupar-se en grups d'opinió o creences similars. Per aquest motiu, el model aprofita el coneixement de la comunitat social en línia al qual pertany el tweeter i supera els resultats obtinguts utilitzant només funcions basades en el contingut de la publicació. És més, els experiments també mostren que els usuaris fan servir diferents tipus de comunicació en funció del nivell d'acord amb l'opinió del seu interlocutor, és a dir, les relacions d'amistat (friendship), retweets i cotitzacions (quotes) són més freqüents entre els usuaris amb idees afins, mentre que les respostes (replies) s'utilitzen sovint per interactuar amb els usuaris que tenen posicions o opinions diferents. A l'hora d'abordar la SD des d'una perspectiva diacrònica, també observem el canvi d'opinió i la mitigació del debat cap a una posició no alineament després del resultat de la votació. A continuació, observem que l'accés a una major diversitat de punts de vista pot influir en la propensió a canviar l'opinió personal. Finalment, mostrem que la utilitat de les funcions basades en una representació gràfica d'un domini d'interès no es limita a la SD, sinó que es pot aplicar a diferents escenaris. Proposar una altra tasca de classificació que realitzi la identificació de talent en l'esport, especialment centrada en l'estudi de cas del tennis de taula, mostrem que les xarxes mètriques basades en la centralitat són un fort senyal per a detectar el talent i també es pot utilitzar per a l'entrenament d'un model d'algorisme d'ap / [EN] In this thesis, we address the problem of stance detection (SD) in social media focusing on polarized political debates in Twitter. SD consists in automatically determine whether the author of a post is in favor or against a target of interest, or whether the opinion toward the given target can not be inferred. We deal with political topics such as electoral events and consequently the targets of interest are both politicians and referendums. We also explore the communications which take place in these polarized debates shedding some light on dynamics of communications among people having concordant or contrasting opinions, particularly focusing on observing opinions' shifting. We propose machine learning models for addressing SD as a classification problem. We explore features based on the textual content of the tweet, but also features based on contextual information that do no emerge directly from the text. Using the English benchmark dataset proposed for the shared tasks on SD held at SemEval 2016, we explore the contribution on SD of investigating the relations among the target of interest and the other entities involved in the debate. Participating to the ``Stance and Gender Detection in Tweets on Catalan Independence'' shared task held at IberEval 2017, we proposed other textual and contextual based features for detecting stance on Spanish and Catalan tweets. With the main aim of facing SD in a multilingual perspective and having an homogeneous setting for multi-language comparisons, we collected tweets in French and Italian also. The multilingual extension of our SD model (multiTACOS) shows that SD is affected by the different styles used by users for communicating stance towards target of different types (persons or referendum) more than the used language. With the aim of retrieving contextual information about the social network of Twitter's users, we created other two datasets, one in English and one in Italian, respectively about the Brexit (TW-BREXIT) and the Italian Constitutional referendum (ConRef-STANCE-ita). In both the case studies, we show that users tend to aggregate themselves in like-minded groups. For this reason, the model takes advantage of knowing the online social community the tweeter belongs to and outperforms the results obtained by using only features based on the content of the post. Furthermore, experiments show that users use different type of communication depending on the level of agreement with the interlocutor's opinion, i.e., friendship, retweets, and quote relations are more common among like-minded users, while replies are often used for interacting with users having different stances. Addressing SD in a diachronic perspective, we also observe both opinion shifting and a mitigation of the debate towards an unaligned position after the outcome of the vote. Then, we observe that accessing to a larger diversity of point of views can influence the propensity to change the personal opinion. We finally show that the usefulness of features based on a graph representation of a domain of interest is not limited to SD, but can be applied to different scenarios. Proposing another classification task that performs talent identification in sport, particularly focusing on the case study of table tennis, we show that networks metrics based on centrality are strong signal for talent and can be used for training a machine learning algorithm model for this task too. / Lai, M. (2019). On Language and Structure in Polarized Communities [Tesis doctoral no publicada]. Universitat Politècnica de València. https://doi.org/10.4995/Thesis/10251/119116 / TESIS