Social media has created a two-pronged dilemma for the journalism world. On one side is an attack of the basic notions of identity and authority for an age-old profession while on the other side supporting journalists by making available an endless amount of new tools and resources for them to work with. This thesis establishes and examines the online community of practice that has formed in the crosshair of the two sides, where the future of newspapers is a hotly debated subject. Using innovative data collection, the conversations of 20 experts is studied qualitatively through computer mediated discourse analysis to examine and explore the debate while providing consideration of the key issues to allow for an in-depth study.

Ingeniero Civil Indusrial / La alta penetración de Twitter en Chile ha favorecido que esta red social sea utilizada por empresas, políticos y organizaciones como un medio para obtener información adicional de las opiniones de usuarios acerca de sus productos, servicios o ellos mismos. Al ser los comentarios en Twitter, por defecto, de carácter público, se pueden analizar con el fin de extraer información accionable. En particular las empresas además de estar interesadas en la información cuantitativa, les interesa saber bajo qué polaridad se efectúan estas menciones, por cuanto una variación positiva en el número de comentarios puede deberse a un mayor número de menciones tanto positivas como negativas. Si bien existen un número considerable de softwares que vienen con la funcionalidad de detección de polaridad de sentimientos, estos no son de mucha utilidad ya que la forma en que interactúa el usuario chileno con esta plataforma está llena de modismos propios de nuestro lenguaje local y abreviaciones que se deben principalmente a la limitación de caracteres de Twitter. Al ser esta una industria inmadura en Chile, la tarea de detección de polaridad de sentimientos, se está realizando de forma manual por agencias publicitarias y otro tipo de empresas, pero dado el gran número de comentarios que se producen minuto a minuto, esta tarea resulta muy demandante en tiempo y dinero. Para resolver este tipo de problemáticas se utilizan técnicas de aprendizaje automático con el fin de entrenar un algoritmo que luego pueda determinar si un comentario es positivo, negativo o neutro, campo que se conoce como sentiment analysis. Mientras más datos sean procesados para el entrenamiento del algoritmo, mejor es el desempeño del clasificador y como en Twitter es sencillo obtener comentarios mediante su API, a diferencia de la web, se han formulado técnicas para generar automáticamente la corpora que contiene los tweets de entrenamiento para cada una de las clases y así sacar provecho de esta propiedad. En este trabajo se profundiza el uso de una metodología semiautomática basada en emoticons para la generación de una corpora de tweets para la detección de polaridad de sentimientos en Twitter. Esto se realiza introduciendo un nuevo enfoque para la consolidación de los datos de entrenamiento mediante filtros que mejoran el etiquetado automático. Esto permite prevenir la aparición de comentarios erráticos y que causan ruido en las fases de entrenamiento y clasificación. Además se introduce una nueva clase de tweets que no se había considerado anteriormente, que consiste de tweets que carecen de información suficiente para clasificarlos como positivos, negativos o neutros, por lo que clasificarlos en alguna de estas clases disminuye la precisión del sistema. Evaluaciones experimentales mostraron que el uso de esta cuarta clase denominada irrelevante con el criterio de filtros presentado para la generación de la corpora, mejora el desempeño del sistema. Además se comprobó experimentalmente que el uso de una corpora generada en base a tweets chilenos clasifican mejor a los comentarios originados por usuarios locales.

Nous proposons dans cette thèse un système permettant de déterminer, à partir des données envoyées sur les microblogs, les évènements qui stimulent l’intérêt des utilisateurs durant une période donnée et les dates saillantes de chaque évènement. Étant donné son taux d’utilisation élevé et l’accessibilité de ses données, nous avons utilisé la plateforme Twitter comme source de nos données. Nous traitons dans ce travail les tweets portant sur la Tunisie dont la plupart sont écrits par des tunisiens. La première tâche de notre système consistait à extraire automatiquement les tweets d’une façon continue durant 67 jours (de 8 février au 15 avril 2012). Nous avons supposé qu’un évènement est représenté par plusieurs termes dont la fréquence augmente brusquement à un ou plusieurs moments durant la période analysée. Le manque des ressources nécessaires pour déterminer les termes (notamment les hashtags) portant sur un même sujet, nous a obligé à proposer des méthodes permettant de regrouper les termes similaires. Pour ce faire, nous avons eu recours à des méthodes phonétiques que nous avons adaptées au mode d’écriture utilisée par les tunisiens, ainsi que des méthodes statistiques. Pour déterminer la validité de nos méthodes, nous avons demandé à des experts, des locuteurs natifs du dialecte tunisien, d’évaluer les résultats retournés par nos méthodes. Ces groupes ont été utilisés pour déterminer le sujet de chaque tweet et/ou étendre les tweets par de nouveaux termes. Enfin, pour sélectionner l'ensemble des évènements (EV), nous nous sommes basés sur trois critères : fréquence, variation et TF-IDF. Les résultats que nous avons obtenus ont montré la robustesse de notre système. / In this thesis, we propose a method to highlight users’ concerns from a set of Twitter messages. In particular, we focus on major events that stimulate the user’s interest within a given period. Given its rate of use and accessibility of data, we used Twitter as a source of our data. In this work, we use tweets related to Tunisia, most of them being written by Tunisians. The first task of our system was to continuously extract tweets during 67 days (from February 8th to April 15th, 2012). We assumed that an event is represented by several terms whose frequency sharply increases one or more times during the analyzed period. Due to the lack of resources that allow determining the terms (including hashtags) referring to the same topic, we propose methods that help grouping similar terms. To do this, we used phonetic methods adapted to the way Tunisians write and statistical methods. To determine the validity of our methods, we asked the experts, who are native speakers of the Tunisian dialect, to evaluate the results returned by our methods. These clusters are used to determine the subject of each tweet and/or expand the tweets by new terms. Finally, to select the set of events (EV), we relied on three criteria: frequency, variation and TF-IDF. The results that we obtained show the robustness of our system.

Since some of the location of where the users posted their tweets collected by social media company have varied accuracy, and some are missing. We want to use those tweets with highest accuracy to help fill in the data of those tweets with incomplete information. To test our algorithm, we used the sets of social media data from a city, we separated them into training sets, where we know all the information, and the testing sets, where we intentionally pretend to not know the location. One prediction method that was used in (Dukler, Han and Wang, 2016) requires appending one-hot encoding of the location to the bag of words matrix to do Location Oriented Nonnegative Matrix Factorization (LONMF). We improve further on this algorithm by introducing iterative LONMF. We found that when the threshold and number of iterations are chosen correctly, we can predict tweets location with higher accuracy than using LONMF.

Syftet med denna uppsats är att undersöka vilka värden som skapas i modehus marknadsföring på sociala medier samt vilken betydelse de värden som skapas har för varumärket. För att besvara syftet undersöks i denna uppsats det franska modehuset Balmain som en fallstudie. Balmains egna- samt huvuddesignern Olivier Rousteings konton på de populära sociala medie-plattformarna Twitter och Instagram analyseras med semiotisk bildanalys baserat på forskningsfrågor om vilka bilder som förekommer, hur relationen mellan bild och text ser ut samt vilka värden som skapas genom inläggen. Som en av forskningsfrågorna lyder, “Hur ser förhållandet mellan bild och text ut enligt Barthes skrivna mode?” så baseras analysen till stor del på Roland Barthes teorier om det skrivna modet i boken The Fashion System (1967/1990). Det skrivna modet är relationen mellan modebild och dess tillhörande bildtext och är till stor nytta vid analysen av det franska modehusets sociala medie-kanaler som till övervägande del består av just modebilder med text till. Resultaten som framkommit är att de fyra flödenas innehåll följer sex övergripande teman: celebritetsstöd, den självständiga kvinnan, relationer, estetik, Olivier Rousteing som maktfull samt gemenskap/inkludering. Genom att anspela på dessa teman i sina inlägg på Instagram och Twitter skapar Balmain sociala-, kulturella-, estetiska och ekonomiska värden. Dessa värden utgör grunden för hur Balmain framställer sig självt som varumärke; ett nytänkande och inbjudande varumärke som fokuserar på att skapa sociala och kulturella värden vilket genererar ekonomiska värden.

There is a significant number of politicians around the globe who demonstrate the conventions of personal style in their political agenda. Norway’s Prime Minister, Jens Stoltenberg or United States’ President, Barack Obama is a few examples. Personalization of politics was reflected through their Twitter account in the notion of content, pictures, and language tone. In the Indonesian political context, Ridwan Kamil became visible as a prominent leader and received immense popularity on Twitter. Social media platforms have changed the way politicians and citizens interact. They are a platform where individuals and communities share, co-create, discuss, and modify user-generated content. Especially with Twitter, certain features such reply, retweet, and hashtag are powerful tools to integrate their political value and construct their persona on Twitter.  This research is conducted by using mixed-method methodologies. The results from content analysis and discourse analysis will complete each other. The results of the content analysis have shown that what Kamil shares on his Twitter profile is mostly about his philosophy about good governance; social media has become a shortcut in the bureaucracy process and at the same time he manages to seem ordinary and authentic with sharing his personal preferences about music or popular culture phenomenon. Discourse analysis is complementing these findings by showing how Kamil deploys language to produce a certain identity. Kamil is crafting his social media skills and shifting from formal to informal tone at every occasion and construct his persona as professional, fun, and caring. All of these results are important inquiries to describe the politician’s presence on Twitter. As the effect of truth, the Twitter user can still relate to Kamil as an ordinary human being. Focusing on the extent to which the content and users’ personality re-fashion political marketing, the study propose how politician integrate their political value and construct their persona on Twitter. As social media grows globally, the phenomenon of politics and social media also appears in Indonesian political sphere especially Twitter as a new space to offer political rhetoric, posturing, and presentational techniques for political agendas.

This article considers emergence in the context of systems of systems, examining the earlier proposed tri-layered architecture in some depth. In contrast with healthcare reform, a social media phenomenon, the emergence of topics in the Twitter user community, is shown not to satisfy a critical condition of the architecture. Nevertheless, detection of topic emergence is shown to offer insights into the design of Emergence Behavior Observers.

The integration of digital technologies in K-12 education is ubiquitous. Web 2.0 technologies enable students who were once passive consumers to become active participants in, and even creators of, dynamic digital experiences. Social media, in particular, can connect disparate populations, minimizing traditional barriers such as time, space and geography. Similarly, science communication has also been influenced by an expanding array of media through which scientists can now connect directly with the public. #Scistuchat, the focus of this study, uses the social media platform Twitter to bring together scientists, secondary science students and teachers outside of school in monthly, science-focused Twitter chats. Using a multiple-case (embedded) design, this study sought to answer the question "How do #scistuchat participants perceive Twitter as a tool for learning and communicating science?" Thematic, cross-case analysis of four #scistuchats revealed themes specific to the #scistuchat experience, as well as the broader use of Twitter for science learning and communication. In addition to real-time observations of each chat and later analysis of the archived tweets, videoconferencing technology was used to conduct individual interviews with participating scientists (n=16) and teachers (n=6), as well as focus groups with students (n=17). Notable #scistuchat-specific findings include a recognition of the experience as dynamic and student-focused. Regarding student outcomes, although gains in science content knowledge were limited, an evolving understanding of scientists and the nature of their work was prominent. Findings regarding the broader use of Twitter for science purposes highlighted its multidimensional, professional utility and its unique contributions when leveraged in classroom settings.

Twitter generates the majority of its revenue from advertising. Third parties pay to have their products advertised on Twitter through: tweets, accounts and trends. However, spammers can use Sybil accounts (fake accounts) [21] to advertise and avoid paying for it. Sybil accounts are highly active on Twitter performing advertising campaigns to serve their clients [5]. They aggressively try to reach a large audience to maximize their influence. These accounts have similar behavior if controlled by the same master. Most of their spam tweets include a shortened URL to trick users into clicking on it. Also, since they share resources with each other, they tend to tweet similar trending topics to attract a larger audience. However, some Sybil accounts do not spam aggressively to avoid being detected [22], rendering it difficult for traditional spam detectors to be effective in detecting low spamming Sybil accounts. In this paper, I investigate additional criteria to measure the similarity between accounts on Twitter. I propose an algorithm to define the correlation among accounts by investigating their tweeting habits and content. Given known labeled accounts by spam detectors, this approach can detect hidden accounts that are closely related to labeled accounts but are not detected by traditional spam detection approaches.

This work concentrates on exploring the influence of social networks to financial markets. We have introduced a novel approach to Twitter sentiment analysis, in which we collect continuous stream of data and analyze it. Our original data set contains over 200 million English written Tweets from the period between July 1, 2014 and October 9, 2014. Twitter sentiment is used as a good representative of investors' mood. On hourly data we investigate how investors are influenced by basic emotions, moods and sentiment in their decision making processes as well as the influence of keywords related to specific securities and FOREX symbols. Particularly, we examine the relationships between Twitter-based variables and returns as well as volatility of several financial instruments on a wide range of data including commodities, currencies and S&P 500 Cash Index. We show that Twitter sentiment influences volatility of securities' returns, tested and shown on both conditional and realized volatility models. We also describe the effect of Twitter sentiment on securities' returns. Moreover, we reveal the influence of basic emotions on investors' decision making processes. Our results suggest that investors are influenced by emotions and moods, especially at longer investment horizons. The impact of emotions at shorter...