As the Web has become integrated into daily life, understanding how individuals spend their time online impacts domains ranging from public policy to marketing. It is difficult, however, to measure even simple aspects of browsing behavior via conventional methods---including surveys and site-level analytics---due to limitations of scale and scope. In part addressing these limitations, large-scale Web panel data are a relatively novel means for investigating patterns of Internet usage. In one of the largest studies of browsing behavior to date, we pair Web histories for 250,000 anonymized individuals with user-level demographics---including age, sex, race, education, and income---to investigate three topics. First, we examine how behavior changes as individuals spend more time online, showing that the heaviest users devote nearly twice as much of their time to social media relative to typical individuals. Second, we revisit the digital divide, finding that the frequency with which individuals turn to the Web for research, news, and healthcare is strongly related to educational background, but not as closely tied to gender and ethnicity. Finally, we demonstrate that browsing histories are a strong signal for inferring user attributes, including ethnicity and household income, a result that may be leveraged to improve ad targeting.

The data made available by Web 2.0 applications such as social networks, on-line chats or blogs have give access to multiples sources of information. Due to this dramatic increase in available information, the perception of quality and credibility plays an important role in social media, thus making necessary to discard low quality and uninteresting content. Moreover, the informal features of Web 2.0 texts such as emoticons, typos, slang or loss of formatting impact negatively on user perception regarding content quality and credibility. For this reason, this paper proposes the SMILE system, a novel unsupervised real-time tool for assessing user-generated content quality and credibility using informality levels. As a test case, we focus on Yahoo! Answers, a relevant Web 2.0 application by its amount of users, content and textual diversity. The results of our study show that informality analysis can be used as criteria to help assess the credibility and quality of Web 2.0 information sources.

We propose a dynamic joint sentiment-topic model (dJST) which allows the detection and tracking of views of current and recurrent interests and shifts in topic and sentiment. Both topic and sentiment dynamics are captured by assuming that the current sentiment-topic specific word distributions are generated according to the word distributions at previous epochs. We derive efficient online inference procedures to sequentially update the model with newly arrived data and show the effectiveness of our proposed model on the Mozilla add-on reviews crawled between 2007 and 2011.

Deluge became a metaphor to describe the amount of information to which we are subjected, and very often we feel we are drowning while our access to information is rising. Devising mechanisms for exploring massive image sets according to perceptual attributes is still a challenge, even more when dealing with user-generated social media content. Such images tend to be heterogenous, and using metadata-only can be misleading. This paper describes a set of tools designed to analyze large sets of user-created art related images using image features describing color, texture, composition and orientation. The proposed pipeline permits to discriminate Flickr groups in terms of feature vectors and clustering parameters. The algorithms are general enough to be applied to other domains in which the main question is about the variability of the images.

We spend a significant part of our lives chatting about other people. In other words, we all gossip. Although sometimes a contentious topic, various researchers have shown gossip to be fundamental to social life—from small groups to large, formal organizations. In this paper, we present the first study of gossip in a large CMC corpus. Adopting the Enron email dataset and natural language techniques, we arrive at four main findings. First, workplace gossip is common at all levels of the organizational hierarchy, with people most likely to gossip with their peers. Moreover, employees at the lowest level play a major role in circulating it. Second, gossip appears as often in personal exchanges as it does in formal business communication. Third, by deriving a power-law relation, we show that it is more likely for an email to contain gossip if targeted to a smaller audience. Finally, we explore the sentiment associated with gossip email, finding that gossip is in fact quite often negative: 2.7 times more frequent than positive gossip.

Most sentiment analysis studies address classification of a single source of data such as reviews or blog posts. However, the multitude of social media sources available for text analysis lends itself naturally to domain adaptation. In this study, we create a dataset spanning three social media sources -- blogs, reviews, and Twitter -- and a set of 37 common topics. We first examine sentiments expressed in these three sources while controlling for the change in topic. Then using this multi-dimensional data we show that when classifying documents in one source (a target source), models trained on other sources of data can be as good as or even better than those trained on the target data. That is, we show that models trained on some social media sources are generalizable to others. All source adaptation models we implement show reviews and Twitter to be the best sources of training data. It is especially useful to know that models trained on Twitter data are generalizable, since, unlike reviews, Twitter is more topically diverse.

Relational classification has been extensively studied recently due to its applications in social, biological, technological, and information networks. Much of the work in relational learning has focused on analyzing input data that comprise a single network. Although machine learning researchers have considered the issue of how to sample training and test sets from the input network (for evaluation), the mechanisms which are used to construct the input networks have largely been ignored. In most cases, the input network has itself been sampled from a larger target network (e.g., Facebook) and often the researcher is unaware of how the input network was constructed or what impact that may have on evaluation of the relational models. Since the goal in evaluating relational classification algorithms is to accurately assess their performance on the larger target network, it is critical to understand what impact the initial sampling method may have on our estimates of classification accuracy.In this paper, we present different sampling methods and systematically study their impact on evaluation of relational classification. Our results indicate that the choice of sampling method can impact classification performance, and thus consequently affects the accuracy of evaluation.

The literature of urban sociology and that of psychology have separately established two relationships: the first has linked characteristics of a community to its residents’ well-being, the second has linked well-being of individuals to their use of words. No one has hitherto explored the potential transitive relationship - that between characteristics of a community and its residents' use of words. We test this relationship by performing three steps. We consider Twitter users in a variety of London census communities; extract the subject matter of their tweets using "topic models"; and study the relationship between topics and community socio-economic well-being. We find that certain topics are correlated (positively and negatively) with community deprivation. Users in more deprived community tweet about wedding parties, matters expressed in Spanish/Portuguese, and celebrity gossips. By contrast, those in less deprived communities tweet about vacations, professional use of social media, environmental issues, sports, and health issues. We finally show that monitoring the subject matter of tweets not only offers insights into community well-being, but it is also a reasonable way of predicting community deprivation scores.

Social media analytics has been attracting considerable attention in both research and industry due to the increasing popularity of social media usage. As a subset, social media monitoring describes the process of continuous monitoring of a subject matter in social media. From our point of view, the key requirements for such systems are i) high throughput and real-time processing of incoming data, ii) a user-friendly way to define complex situations of interests that make use of formalized background knowledge and iii) capabilities to perform actions based on gained insights instead of a pure monitoring system. In this paper, we propose a system for (pro) active, real-time social media monitoring. Firstly, we describe the conceptual architecture of our system and necessary pre-processing steps. Secondly, we introduce our concept of semantic requests that is capable to extend event pattern definitions with background knowledge. Finally, we show the usefulness of this system in two different domains: Real-time political opinion tracking and proactive establishment of relationships with consumers in order to perform a new form of real-time marketing. The main advantage of our approach is a simplified, expressive way to formulate event patterns in social media applications.

Reactions to textual content posted in an online social net- work show different dynamics depending on the linguistic style and readability of the submitted content. Do similar dy- namics exist for responses to scientific articles? Our intuition, supported by previous research, suggests that the success of a scientific article depends on its content, rather than on its linguistic style. In this article, we examine a corpus of sci- entific abstracts and three forms of associated reactions: ar- ticle downloads, citations, and bookmarks. Through a class- based psycholinguistic analysis and readability indices tests, we show that certain stylistic and readability features of ab- stracts clearly concur in determining the success and viral ca- pability of a scientific article.