Många företag använder Twitter i sin marknadskommunikation, men misslyckas. Uppsatsen syftar till att belysa ett e-handelsföretag, Sportamore, i Sverige som använder plattformen i dess fulla potential och därmed skapar vänskapsrelationer. Uppsatsen baseras på en dialogisk analys av tweets till och från e-handelsbolaget under åren 2010, 2012, 2014. Det är en kvalitativ studie med ett hermeneutiskt perspektiv. Resultatet visar hur ett företag med hjälp av dialog kan skapa mervärde och relationer på Twitter. Studien visar hur relationerna bidrar till att företagets kunder kontinuerligt marknadsför företaget på plattformen. Twitter blir därmed en Silver Bullet i företagets marknadsföring då arbetet på plattformen inte syftar till ekonomisk lönsamhet utan snarare relationsskapande. Studien avser inte att undersöka vad företag gör som är dåligt på Twitter utan fokuserar på vad som är lyckosamt för att skapa relationer via dialog. Relationsskapande är viktigt då marknadsföring och public relations har ändrat karaktär. I och med att mängden marknadsföring, och kanaler för marknadsföring, har ökat är det svårare än någonsin för företag att nå genom bruset. Det är alltså viktigt att företagens marknadskommunikation anpassas efter nya förutsättningar. / Lots of corporations use Twitter in their marketing - but fail to succeed. This essay´s purpose is to illuminate a corporation that is positioned as an e-commerce company, which uses Twitter to its full potential and thereby creating friendships with their followers. This is a qualitative study based on a dialogic analysis of the interaction on Twitter to and from the account @sportamore during the years 2010, 2012 and 2014. This study shows how corporations can use dialogic strategies on Twitter to create value and relations with their followers. It also shows that relations, or friendship, leads to that followers are continually marketing Sportamore within tweets and in interaction with others. Twitter with its primary purpose of developing relations becomes a Silver Bullet for marketers when Twitters not about making economic profit. This study does not have the purpose to search for weaknesses in the communication of Sportamore on Twitter. In order to the fact that marketing and public relations are re-shaping and its harder for corporations to reach trough the clutter of campaigns, social media and marketing – relationship building is important in today´s marketing efforts.

Background: Twitter, Facebook, WordPress, etc. act as the major sources of information exchange in today's world. The tweets on Twitter are mainly based on the public opinion on a product, event or topic and thus contains large volumes of unprocessed data. Synthesis and Analysis of this data is very important and difficult due to the size of the dataset. Sentiment analysis is chosen as the apt method to analyse this data as this method does not go through all the tweets but rather relates to the sentiments of these tweets in terms of positive, negative and neutral opinions. Sentiment Analysis is normally performed in 3 ways namely Machine learning-based approach, Sentiment lexicon-based approach, and Hybrid approach. The Machine learning based approach uses machine learning algorithms and deep learning algorithms for analysing the data, whereas the sentiment lexicon-based approach uses lexicons in analysing the data and they contain vocabulary of positive and negative words. The Hybrid approach uses a combination of both Machine learning and sentiment lexicon approach for classification. Objectives: The primary objectives of this research are: To identify the algorithms and metrics for evaluating the performance of Machine Learning Classifiers. To compare the metrics from the identified algorithms depending on the size of the dataset that affects the performance of the best-suited algorithm for sentiment analysis. Method: The method chosen to address the research questions is Experiment. Through which the identified algorithms are evaluated with the selected metrics. Results: The identified machine learning algorithms are Naïve Bayes, Random Forest, XGBoost and the deep learning algorithm is CNN-LSTM. The algorithms are evaluated with respect to the metrics namely precision, accuracy, F1 score, recall and compared. CNN-LSTM model is best suited for sentiment analysis on twitter data with respect to the selected size of the dataset. Conclusion: Through the analysis of results, the aim of this research is achieved in identifying the best-suited algorithm for sentiment analysis on twitter data with respect to the selected dataset. CNN-LSTM model results in having the highest accuracy of 88% among the selected algorithms for the sentiment analysis of Twitter data with respect to the selected dataset.

Made available in DSpace on 2016-04-28T19:33:51Z (GMT). No. of bitstreams: 1 Tharsila Dantas Prates.pdf: 3487333 bytes, checksum: 0704472d812a2abbfb50ccad492e63bd (MD5) Previous issue date: 2014-09-02 / The present work is in the line of research Reading, writing and teaching of Portuguese. The theme is the use of the microblogging service Twitter for writing s activities to grade school students. The aim of this work is to propose activities using Twitter for Portuguese classes. The specific objectives are: describe the Twitter and propose writing s activities that permit a concise writing and that prepare the students to summarization of texts. The theoretical base is the research in Textual Linguistics at the social, cognitive and interactional perspective, used for define textual coherence (BEAUGRANDE & DRESSLER, 1981; BEAUGRANDE, 1997; KOCH & TRAVAGLIA, 2011, 2012); show the standards of textuality (BEAUGRANDE & DRESSLER, 1981; KOCH & TRAVAGLIA, 2011, 2012); the macrostructure or the principal idea of text (VAN DIJK, 2008) and the roles to reduce semantic information (VAN DIJK & KINTSCH, 1975). In the presence of access to new technologies and the need of teaching of concise and coherent writing, we developed a proposal with the use of Twitter to be applied to an opinion article sort of text worked by educators in nine year of grade school. We believe that microblogging can be an aid to the Portuguese teacher make students develop the power of synthesis and writing coherently / Este trabalho insere-se na linha de pesquisa Leitura, escrita e ensino de Língua Portuguesa e tem como tema a utilização do microblog Twitter em atividades de escrita voltadas a alunos do 9º ano do Ensino Fundamental. O objetivo geral é apresentar uma proposta de utilização do Twitter nas aulas de Língua Portuguesa. Os objetivos específicos são: identificar recursos que o microblog Twitter oferece e propor atividades que permitam ao aluno o exercício da síntese e a preparação para a escrita de resumo. Para desenvolvermos a proposta, embasamo-nos na perspectiva sociocognitivo-interacional da Linguística Textual no que diz respeito a aspectos da coerência textual, tais como: sua definição (BEAUGRANDE & DRESSLER, 1981; BEAUGRANDE, 1997; KOCH & TRAVAGLIA, 2011, 2012); os fatores que contribuem para essa coerência (BEAUGRANDE & DRESSLER, 1981; KOCH & TRAVAGLIA, 2011, 2012); a identificação da macroestrutura ou ideia principal do texto (VAN DIJK, 2008) e as regras de redução da informação semântica (VAN DIJK & KINTSCH, 1975). Diante da possibilidade de acesso às novas tecnologias e da necessidade do ensino da escrita coerente e concisa, desenvolvemos uma proposta com o uso do Twitter, para ser aplicada a um artigo de opinião, gênero trabalhado no último ano do Ensino Fundamental na Rede Municipal de São Paulo. Acreditamos que o microblog pode constituir um auxílio ao professor de Língua Portuguesa para fazer com que o educando desenvolva o poder de síntese e a escrita com coerência

Made available in DSpace on 2016-10-13T14:10:06Z (GMT). No. of bitstreams: 1 Flavia Totoli.pdf: 7289958 bytes, checksum: a04eff7e600b2cd6e26f0ba6c721665d (MD5) Previous issue date: 2012-03-15 / The present study investigated whether the use of social media, particularly Twitter promote customer loyalty to the company. To that end, we organized a theoretical construct, which showed the chain of concepts based on the literature reviewed. In order to examine the consistency of the proposed relationship, this research determined as a methodology, a triangulation of qualitative and quantitative research. The first phase was the completion of a survey that examined the issue of customer loyalty to Twitter. Then, we carried out a desk research, in which were gathered and analyzed the contents of the Twitter profiles of selected companies (Microsoft, Intel, Google and IBM). The expected result for this field research was the confirmation of the theoretical construct. The contribution that produced this dissertation was to develop a model of loyalty, based on the use of Twitter. Initially we present the first chapter with an introduction to research the problem, the goal, s assumptions and reasoning behind the study. The second chapter is to review theoretical, which are presented in the following variables: social media, interactivity, relationship and loyalty, concluding with the presentation of a theoretical construct developed based on literature gathered. The third chapter describes the methodology chosen, in a triangulation for the survey field. Presented the rationale of the study and epistemological choices made ​​by the author. The fourth chapter shows the analysis and interpretation of quantitative research and qualitative. Next, the fifth chapter presents the conclusions and the sixth chapter presents the research limitations and suggestions for advancing the same. / A presente pesquisa investigou se a utilização das mídias sociais, em particular, o Twitter promovem lealdade do cliente para com a empresa. Para tanto foi organizado um constructo teórico, que apresentou o encadeamento de conceitos baseado na literatura revisada. Com o objetivo de examinar a consistência da relação proposta, esta investigação determinou como metodologia, uma triangulação de pesquisas qualitativas e quantitativas. A primeira fase foi a realização de uma survey, que analisou a questão da fidelidade dos usuários ao Twitter. Em seguida, foi realizada uma pesquisa documental, na qual foram reunidos e analisados os conteúdos dos perfis de Twitter das empresas escolhidas (Microsoft, Intel, Google e IBM). O resultado esperado para esta pesquisa de campo era a confirmação do constructo teórico. A contribuição que essa dissertação produziu foi o desenvolvimento de um modelo de lealdade, baseado na utilização do Twitter. Inicialmente apresenta-se o primeiro capítulo com uma introdução a pesquisa, o problema, o objetivo, s hipóteses e justificativas do estudo. O segundo capítulo consiste na revisão teórica, na qual são apresentadas as seguintes variáveis: mídias sociais, interatividade, relacionamento e lealdade, concluindo com a apresentação de um constructo teórico desenvolvido com base na literatura reunida. O terceiro capítulo descreveu a metodologia escolhida, uma na triangulação para a pesquisa de campo. Apresentou-se a justificativa do estudo e as escolhas epistemológicas feitas pela autora. O quarto capítulo exibe a análise e interpretação dos dados das pesquisas quantitativas e qualitativas. Na seqüência, o quinto capítulo apresenta as considerações finais, e o sexto capítulo apresenta as limitações da pesquisa e sugestões para o avanço da mesma.

Made available in DSpace on 2016-04-26T18:13:15Z (GMT). No. of bitstreams: 1 Pedro da Cunha Del Picchia.pdf: 1973312 bytes, checksum: c5d2c263dccd15795c0b3253c4aa4a57 (MD5) Previous issue date: 2013-05-24 / This research aims to further the understanding of the relationship between on and offline personalities in digital social networks. It focuses on the behavior of users from the online social network Twitter. This network was specifically chosen because it provides not only comunicational relevance but also three distinguishing characteristics. The first is an unique freedom to create an avatar. The second is a high speed in the exchange of messages, which is significant because of the premisse that relevant users are those that interact frequently with the network. And, finally, an also unique following/follower structure, which promotes the emergence of leaders and subgroups. The theoretical framework is based on the concepts of digital-glocal environments proposed by Trivinho Dal Bello (2009), digital avatars as defined by Cavalheiro in his master's dissertation (2008), Lazarsfeld's (1995) theory of two-step-flow of information and also in a context analysis of the freudian theory presented in Mass Psychology (1921). The hypothesis is that the creation of an avatar personality follows influence and leadership patterns. The methodology is based on an analysis of widely shared posts from several users and interviews with three study participants who have popular avatars in Twitter / A presente pesquisa tem como objetivo a compreensão, dentro das redes sociais digitais, da relação de uma personalidade on-line com a personalidade off-line. O seu objeto de estudo é o comportamento dos usuários da Rede Social na Internet Twitter, já que esta, além da sua relevância comunicacional, possui três aspectos que lhe distinguem: a liberdade singular na criação do avatar; a velocidade na troca de mensagens, uma vez que parto da proposta de que o usuário, para ter relevância, deve interagir com frequência em sua rede; e a estrutura proposta de seguidor-seguido, que é única e promove a formação de lideranças e subgrupos. A fundamentação teórica apoia-se no enquadramento de construção do ambiente digital-glocal proposto por Trivinho e Dal Bello (2009), no conceito de avatar digital apresentado por Cavalheiro em sua dissertação de mestrado (2008), em uma análise de contexto sob a ótica de Freud em seu texto Psicologia de Grupo (1921), bem como do fluxo de informação em two-step flow proposto por Lazarsfeld (1955). A hipótese é a de que a própria criação desta personalidade-avatarizada segue por padrões de influência e liderança. A metodologia se desenvolve por meio da análise de publicações de diversos usuários que se destacaram a partir do número de republicações e entrevistas com três personagens, cujos avatares têm grande exposição dentro do Twitter

Den här studien behandlar fenomenet sociala medier med inriktning på att öka trafik till detaljhandelns webbaserade sidor för att skapa relationer, bygga varumärke och öka försäljning.Idag står företag inför en ny utmaning när det gäller marknadsföring. På några få år har internethandeln exploderat och med det företagens sätt att marknadsföra sig virtuellt. Sedan början av 2000-talet har en ny kanal för att sända ut marknadsföringsmässiga budskap till kunderna uppstått, de sociala medierna. Ett exempel på en av dessa är Facebook vars användarantal bara stiger år för år och i dagsläget har fler än 6 av 10 svenskar en personprofil på Facebook.Varje kanal för kommunikation har sina egenskaper och med det givna referensramar för företagen att arbeta med och skapa verktyg för. Då sociala medier fortfarande är ett ganska nytt fenomen anser vi att problematiken ligger i att många företag inte har hittat det ultimata användningssättet för kanalen. Exempelvis finns många företag representerade på Facebook, men att bara ha en profil gör varken till eller från om de inte fyller sitt budskap till kunderna med innehåll. De måste vara aktiva med sitt sociala företagande för att kunna nå fram i bruset.Med den nya tekniken uppstår både möjligheter och komplikationer i hur företagen bättre kan skapa en relation till sina kunder. Klassiska modeller som kommunikationsmodellen, relationsmarknadsföring och word of mouth är fungerande teorier för det nya fältet då det grundar sig på ett uråldrigt fenomen – kommunikation. Tillsammans bildar de här tre teorierna vår teoretiska referensram.En social media kännetecknas av sin förmåga att skapa interaktiv kommunikation. Förr sände företagen ut ett budskap till en tänkt målgrupp och hoppades att den skulle nå fram och tolkas rätt genom bruset på vägen. Idag erbjuds en tvåvägskommunikation där kunderna har möjlighet att sända sin feedback tillbaka till företagen. Via internetanvändarnas på klick skapas en trafik som är mätbar för hur framgångsrik till exempel en kampanj är för ett företag. Den här studien utreder de vanligast förekommande begreppen inom internettrafik för att underlätta förståelsen av fältet.Via empiriska data som behandlar några av de största sociala plattformarna i samhället idag: Facebook, bloggar och Twitter, belyser vi fältet ur användarens såväl som företagets perspektiv. Informationen är hämtad ur adekvat litteratur i ämnet samt akademiskt granskade artiklar. För att få en större tyngd i studien har vi genomfört kvalitativa intervjuer med människor som har erfarenhet från branschen.Slutsatsen vi har dragit från vår studie är att om företagen ska använda sig av sociala medier är det viktigt att ha i åtanke att den här kanalen inte skiljer såg från andra, då det gäller att nå fram med sitt budskap. Myten om att sociala medier utgör en gratis kommunikationskanal stämmer inte, då ett välgjort budskap endast kan uppnås då det ligger tid och energi bakom från företagens sida. För få spridning på budskapet och uppnå word of mouth måste företagen erbjuda användarna något som inspirerar dem att sprida informationen vidare.This study deals with the phenomenon social media with an emphasis on the increased web traffic to retail trade companies’ web pages to better create relationships to their customers, add value to their brands and enhance their sales numbers.Today’s companies are fronting a new marketing challenge. In a few years the online commerce has exploded and with it the companies’ strategies to market themselves virtually. Since the beginning of the early 21st century a new channel has arisen for advertising messages; the social media. An example of such media is the social networking page Facebook whose number of users is increasing day by day. Today 6 out of 10 Swedes have a Facebook profile of their own.Each channel for communication implies a capacity of its own in the terms of marketing tools for companies to use. Social media is however a new communication tool for many companies and the complex of problems is that they have not properly learnt how to use it. A lot of companies are represented on Facebook commercially; only the bare existing on Facebook does not contribute to the company’s development, if they do not fill their messages with meaning and content. To be able to reach their customers companies have to work actively to promote them selves through the social media channel.The new technology carries both possibilities and complications for the companies to enhance their relationship to their customers. Classic models of theory such as the communication model, relationship marketing and word of mouth are still useful to the new field of study because it is based on an ancient phenomenon – communication. Together these three theories constitute our frame of reference.A social media is described by its ability to create interactive communication. Not long ago the companies would send out their advertising message through traditional marketing channels hoping that their message would be received and understood by their group of interest through the noise. Today’s social media model offers an interactive communication that facilitates the receiving of feedback from customers. Through the business model of Internet traffic, which measures customers’ clicks and thereby their interest, the success of a social media campaign is perceived. This study investigates how the most common traffic business models are used on the Internet to better fill the reader in on the field of study.The empirical data discusses some of the most used social networking sites worldwide today. The social media platforms described, both through the eyes of the Internet user and the company, are: Facebook, Twitter and blogs. The information presented in the study has its origin from peer reviewed articles and adequate literature. To better establish the understanding of the field of study the authors have accomplished qualitative interviews with people from the line of business.Our conclusion drawn from the study is that if companies wish to present themselves on social media they have to commit to the new way of marketing that this channel of communication offers. The myth of social media being practically a free marketing channel is eliminated by the fact that success in any communication channel depends on effort, energy, time and money. To create word of mouth companies have to offer the user of social media something that inspires them and that creates something they wish to share. / Program: Textilekonomutbildningen

O crescente uso de redes sociais gera quantidades enormes de dados que podem ser empregados em vários tipos de análises. Alguns desses dados têm informação temporal e geográfica, as quais podem ser usadas para posicionar precisamente a informação no tempo e no espaço. Nesse contexto, neste trabalho é proposto um novo método para a análise do volume massivo de mensagens disponível no Twitter, com o objetivo de identificar eventos como programas de TV, mudanças climáticas, desastres e eventos esportivos que estejam ocorrendo em regiões específicas do globo. A abordagem proposta é baseada no uso de uma rede neural para detecção de outliers em séries temporais, as quais são formadas por estatísticas coletadas em tweets localizados em diferentes divisões políticas (i.e., países, cidades). Esses outliers são usados para identificar eventos como um comportamento anormal nos dados Twitter. A efetividade do método é avaliada comparando os eventos identificados com notícias nos meios de comunicação. / The increasing use of social networks generates enormous amounts of data that can be employed for various types of analysis. Some of these data have temporal and geographical information, which can be used to precisely position information in time and space. In this document, a new method is proposed to analyze the massive volume of messages available in Twitter to identify events such as TV shows, climate change, disasters, and sports that are occurring in specific regions of the globe. The proposed approach is based on a neural network used to detect outliers from a time series, which is built upon statistical data from tweets located in different political divisions (i.e., countries, cities). These outliers are used to identify events as an abnormal behavior in Twitter's data. The effectiveness of the method is evaluated by comparing the events identified on the news media.

L'étude de l'influence sur les réseaux sociaux et en particulier Twitter est un sujet de recherche intense. La détection des utilisateurs influents dans un réseau est une clé de succès pour parvenir à une diffusion d'information à large échelle et à faible coût, ce qui s'avère très utile dans le marketing ou les campagnes politiques. Dans cette thèse, nous proposons une nouvelle approche qui tient compte de la variété des relations entre utilisateurs afin d'estimer l'influence dans les réseaux sociaux tels que Twitter. Nous modélisons Twitter comme un réseau multiplexe hétérogène où les utilisateurs, les tweets et les objets représentent les noeuds, et les liens modélisent les différentes relations entre eux (par exemple, retweets, mentions et réponses). Le PageRank multiplexe est appliqué aux données issues de deux corpus relatifs au domaine politique pour classer les candidats selon leur influence. Si le classement des candidats reflète la réalité, les scores de PageRank multiplexe sont difficiles à interpréter car ils sont très proches les uns des autres.Ainsi, nous voulons aller au-delà d'une mesure quantitative et nous explorons comment les différentes relations entre les noeuds du réseau peuvent déterminer un degré d'influence pondéré par une estimation de la crédibilité. Nous proposons une approche, TwitBelief, basée sur la règle de combinaison conjonctive de la théorie des fonctions de croyance qui permet de combiner différents types de relations tout en exprimant l’incertitude sur leur importance relative. Nous expérimentons TwitBelief sur une grande quantité de données collectées lors des élections européennes de 2014 et de l'élection présidentielle française de 2017 et nous déterminons les candidats les plus influents. Les résultats montrent que notre modèle est suffisamment flexible pour répondre aux besoins des spécialistes en sciences sociales et que l'utilisation de la théorie des fonctions de croyances est pertinente pour traiter des relations multiples. Nous évaluons également l'approche sur l'ensemble de données CLEF RepLab 2014 et montrons que notre approche conduit à des résultats significatifs. Nous proposons aussi deux extensions de TwitBelief traitant le contenu des tweets. La première est l'estimation de la polarisation de l'influence sur le réseau Twitter en utilisant l'analyse des sentiments avec l'algorithme des forêts d'arbres décisionnels. La deuxième extension est la catégorisation des styles de communication dans Twitter, il s'agit de déterminer si le style de communication des utilisateurs de Twitter est informatif, interactif ou équilibré. / Influence in complex networks and in particular Twitter has become recently a hot research topic. Detecting most influential users leads to reach a large-scale information diffusion area at low cost, something very useful in marketing or political campaigns. In this thesis, we propose a new approach that considers the several relations between users in order to assess influence in complex networks such as Twitter. We model Twitter as a multiplex heterogeneous network where users, tweets and objects are represented by nodes, and links model the different relations between them (e.g., retweets, mentions, and replies).The multiplex PageRank is applied to data from two datasets in the political field to rank candidates according to their influence. Even though the candidates' ranking reflects the reality, the multiplex PageRank scores are difficult to interpret because they are very close to each other.Thus, we want to go beyond a quantitative measure and we explore how relations between nodes in the network could reveal about the influence and propose TwitBelief, an approach to assess weighted influence of a certain node. This is based on the conjunctive combination rule from the belief functions theory that allow to combine different types of relations while expressing uncertainty about their importance weights. We experiment TwitBelief on a large amount of data gathered from Twitter during the European Elections 2014 and the French 2017 elections and deduce top influential candidates. The results show that our model is flexible enough to consider multiple interactions combination according to social scientists needs or requirements and that the numerical results of the belief theory are accurate. We also evaluate the approach over the CLEF RepLab 2014 data set and show that our approach leads to quite interesting results. We also propose two extensions of TwitBelief in order to consider the tweets content. The first is the estimation of polarized influence in Twitter network. In this extension, sentiment analysis of the tweets with the algorithm of forest decision trees allows to determine the influence polarity. The second extension is the categorization of communication styles in Twitter, it determines whether the communication style of Twitter users is informative, interactive or balanced.

Social media has become an important marketing and communication tool worldwide, mostly through the largest social platforms Facebook and Twitter. With two-way communication via Internet companies has gotten the opportunity to interact and communicate directly with their customers. Facebook has been the focus point through the study because it has shown to be the most efficient and frequently used platform for communication. Our study aimed to confirm how communication via social media actually looks like. To be able to reach the best results, we have conducted the study from a phenomenological approach, which means; usage of qualitative semi-structured interviews to reflect the respondents experience on the phenomenon social media as a communication tool. Social media has shown to be a great way of communicating externally for companies who are willing to spend time engaging in the platform. The opportunities social media has brought, such as interaction has led most of the companies to use social media as their primary communication channel, all thou social media is probably not going to replace the traditional channels. This study has also allowed us to develop a model for communication through social media, for companies who are thinking of communicating through social media, and for companies who are communicating through social media today.

Our digital society encompasses nowadays different channels, which includes social media where many users consider it as a platform where they can fetch news or exchange news and information. This leads to a large spread of news exchange in a very fast speed, which involves the global users within social media to be a part of this social interaction. This study is focused on how Twitter affects the usage of the user’s news consumption. By reaching out to our specific target audience, which includes Twitter users in Sweden, we made a web based survey with a content of relevant questions. The study has been conducted through a quantitative survey with qualitative elements. We have used theories of mass communication and Uses and Gratifications to describe the development in the area of Twitter usage and their news consumption. The results show that the users’ news consumption has increased since their registration on Twitter and that their total daily news input comes of a large part from this platform.