Im Social Commerce entwickeln sich die Kunden zu einer bedeutenden Informationsquelle für Unternehmen. Die Kunden nutzen die Kommunikationsplattformen des Web 2.0 (z.B. Twitter), um ihre Meinungen und Erfahrungen über Produkte zu äußern. Diese Diskussionen können sehr wichtig für die Entwicklung von Produkten eines Unternehmens sein. Ein modellbasierter Ansatz soll es einem Unternehmen ermöglichen, die Meinungen zu seinen Produkten in Microblogs zu betrachten. Der erste Schritt dafür ist die Erkennung von Themen in einem spezifischen Kontext. In einem weiteren Schritt müssen die zu den Themen korrespondierenden Einträge bezüglich der geäußerten Meinungen analysiert werden. Für die Erkennung der Themen kommt ein Verfahren zum Einsatz, das auf der Latent Dirichlet Allocation basiert. Das Verfahren identifizierte eventbasierte Themen im Zusammenhang mit den 3D-TV-Anlagen von Sony.

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.

Search and summarization of streaming social media, such as Twitter, requires the ongoing analysis of large volumes of data with dynamically changing characteristics. Tweets are short and repetitious -- lacking context and structure -- making it difficult to generate a coherent synopsis of events within a given time period. Although some established algorithms for frequent itemset analysis might provide an efficient foundation for synopsis generation, the unmodified application of standard methods produces a complex mass of rules, dominated by common language constructs and many trivial variations on topically related results. Moreover, these results are not necessarily specific to events within the time period of interest. To address these problems, we build upon the Linear time Closed itemset Mining (LCM) algorithm, which is particularly suited to the large and sparse vocabulary of tweets. LCM generates only closed itemsets, providing an immediate reduction in the number of trivial results. To reduce the impact of function words and common language constructs, we apply a filltering step that preserves these terms only when they may form part of a relevant collocation. To further reduce trivial results, we propose a novel strengthening of the closure condition of LCM to retain only those results that exceed a threshold of distinctiveness. Finally, we perform temporal ranking, based on information gain, to identify results that are particularly relevant to the time period of interest. We evaluate our work over a collection of tweets gathered in late 2012, exploring the efficiency and filtering characteristic of each processing step, both individually and collectively. Based on our experience, the resulting synopses from various time periods provide understandable and meaningful pictures of events within those periods, with potential application to tasks such as temporal summarization and query expansion for search.

Search and summarization of streaming social media, such as Twitter, requires the ongoing analysis of large volumes of data with dynamically changing characteristics. Tweets are short and repetitious -- lacking context and structure -- making it difficult to generate a coherent synopsis of events within a given time period. Although some established algorithms for frequent itemset analysis might provide an efficient foundation for synopsis generation, the unmodified application of standard methods produces a complex mass of rules, dominated by common language constructs and many trivial variations on topically related results. Moreover, these results are not necessarily specific to events within the time period of interest. To address these problems, we build upon the Linear time Closed itemset Mining (LCM) algorithm, which is particularly suited to the large and sparse vocabulary of tweets. LCM generates only closed itemsets, providing an immediate reduction in the number of trivial results. To reduce the impact of function words and common language constructs, we apply a filltering step that preserves these terms only when they may form part of a relevant collocation. To further reduce trivial results, we propose a novel strengthening of the closure condition of LCM to retain only those results that exceed a threshold of distinctiveness. Finally, we perform temporal ranking, based on information gain, to identify results that are particularly relevant to the time period of interest. We evaluate our work over a collection of tweets gathered in late 2012, exploring the efficiency and filtering characteristic of each processing step, both individually and collectively. Based on our experience, the resulting synopses from various time periods provide understandable and meaningful pictures of events within those periods, with potential application to tasks such as temporal summarization and query expansion for search.

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.

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.

In this diploma thesis I deal with the topic of blogs. My main goal was to introduce the part of blogs called mommyblogs and to define it as a separate category in the theoretical background chapter. In the practical part, I decided to use quantitative methods of data collection through a questionnaire survey. The survey was aimed at both mommy bloggers and their readers. I supplemented the questionnaires with depth interviews with selected mommy bloggers. Which helped me to obtain even more detailed data, which enriched the data obtained from both questionnaires. I found out what motivates mommy bloggers to blog, but also what their attitude is towards cooperation with companies and how they select and label collaborations. Have they ever felt exploited either by companies or by social media? The respondents also touched on the topic of ethics and responsibility - either regarding the placement of photos of children on social media or regarding products whose promotion is bound by regulations. I tried to find out the ability of the readers to recognize advertisements on blogs and social networks of mommy bloggers. And also how the advertising message of mommy bloggers affects their readers. This thesis focuses only on bloggers from the Czech Republic.

No description available.

Twitter has quickly become one of the most popular social media sites. It has 313 million monthly active users, and 500 million tweets are published daily. With the massive number of tweets, Twitter users share information about a location along with the temporal awareness. In this work, I focus on tweets where author of the tweets exclusively mentions a location in the tweet. Natural language processing systems can leverage wide range of information from the tweets to build applications like recommender systems that predict the location of the author. This kind of system can be used to increase the visibility of the targeted audience and can also provide recommendations interesting places to visit, hotels to stay, restaurants to eat, targeted on-line advertising, and co-traveler matching based on the temporal information extracted from a tweet. In this work I determine if the author of the tweet is present in the mentioned location of the tweet. I also determine if the author is present in the location before tweeting, while tweeting, or after tweeting. I introduce 5 temporal tags (before the tweet but > 24 hours; before the tweet but < 24 hours; during the tweet is posted; after the tweet is posted but < 24 hours; and after the tweet is posted but > 24 hours). The major contributions of this paper are: (1) creation of a corpus of 1062 tweets containing 1200 location named entities, containing annotations whether author of a tweet is or is not located in the location he tweets about with respect to 5 temporal tags; (2) detailed corpus analysis including real annotation examples and label distributions per temporal tag; (3) detailed inter-annotator agreements, including Cohen's kappa, Krippendorff's alpha and confusion matrices per temporal tag; (4) label distributions and analysis; and (5) supervised learning experiments, along with the results.

No description available.