The recent prominence of the real-time web is proving both challenging and disruptive for information retrieval and web data mining research. User-generated content on the real-time web is perhaps best epitomised by content on microblogging platforms, such as Twitter. Given the substantial quantity of microblog posts that may be relevant to a user's query at a point in time, automated methods are required to sift through this information. Sentiment analysis offers a promising direction for modelling microblog content. We build and evaluate a sentiment-based filtering system using real-time user studies. We find a significant role played by sentiment in the search scenarios, observing detrimental effects in filtering out certain sentiment types. We make a series of observations regarding associations between document-level sentiment and user feedback, including associations with user profile attributes, and users' prior topic sentiment.

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.

This paper reports ongoing work in the “Networks of Texts and People” project, which is developing methods to visualize the social and epistemological contexts of information contained in blogs. Here, we propose an approach to visualize information diffusion and polarization in the blogosphere, with two novel characteristics. Firstly, we demonstrate how text content can be analyzed and visualized as key statements, rather than as keywords. Secondly, we sketch and discuss ideas for a visual analytic tool that integrates data about blog networks with data about the occurrence of related key statements in blog posts.

Twitter, used in 200 countries with over 250 milliontweets a day, is a rich source of local news from aroundthe world. Many events of local importance are first reportedon Twitter, including many that never reach newschannels. Further, there are often only a few tweetsreporting each such event, in contrast with the largervolumes that follow events of wider significance. Eventhough such events may be primarily of local importance,they can also be of critical interest to some specificbut possibly far flung entities: For example, a firein a supplier’s factory half-way around the world maybe of interest even from afar. In this paper we describehow this ‘long tail’ of events can be detected in spite oftheir sparsity.We then extract and correlate informationfrom multiple tweets describing the same event. Ourgeneric architecture for converting a tweet-stream intoevent-objects uses locality sensitive hashing, classification,boosting, information extraction and clustering.Our results, based on millions of tweets monitored overmany months, appear to validate our approach and architecture:We achieved success-rates in the 80% rangefor event detection and 76% on event-correlation; we also reduced tweet-comparisons by 80% using LSH.

News articles are extremely time sensitive by nature. There is also intense competition among news items to propagate as widely as possible. Hence, the task of predicting the popularity of news items on the social web is both interesting and challenging. Prior research has dealt with predicting eventual online popularity based on early popularity. It is most desirable, however, to predict the popularity of items prior to their release, fostering the possibility of appropriate decision making to modify an article and the manner of its publication. In this paper, we construct a multi-dimensional feature space derived from properties of an article and evaluate the efficacy of these features to serve as predictors of online popularity. We examine both regression and classification algorithms and demonstrate that despite randomness in human behavior, it is possible to predict ranges of popularity on twitter with an overall 84% accuracy. Our study also serves to illustrate the differences between traditionally prominent sources and those immensely popular on the social web.

Social media plays an important role in the process of political engagement, especially in societies where significant constraints over traditional media and participation still exist. Little is known about how social media use is related to these constraints. This study examines how citizens’ perceptions of government control predict social media use and how this use is related to offline participation in the context of a city-state, Singapore. Based on a national survey of 2000 respondents, we found that perceptions of control over traditional media and political activity increase content production on social media and that perceived control of the mass media motivates citizens to consume political content on social media. Interestingly, perceptions of government control over the Internet reduced rather than increased social media production. More importantly, we find that social media use is related to a greater likelihood of offline citizen participation, namely attendance of political rallies. The findings suggest that social media alters the balance of power in the dependency relationships that exist between the government, media organizations and citizens, creating new venues for online political discourse which in turn help promote real-world political participation.

We describe a simple IR approach for linking news about events, detected by an event extraction system, to messages from Twitter (tweets). In particular, we explore several methods for creating event-specific queries for Twitter and provide a quantitative and qualitative evaluation of the relevance and usefulness of the information obtained from the tweets. We showed that methods based on utilization of word co-occurrence clustering, domain-specific keywords and named entity recognition improve the performance with respect to a basic approach.

The problem of automatic extraction of sentiment expressions from informal text, as in microblogs such as tweets is a recent area of investigation. Compared to formal text, such as in product reviews or news articles, one of the key challenges lies in the wide diversity and informal nature of sentiment expressions that cannot be trivially enumerated or captured using predefined lexical patterns. In this work, we present an optimization-based approach to automatically extract sentiment expressions for a given target (e.g., movie, or person) from a corpus of unlabeled tweets. Specifically, we make three contributions: (i) we recognize a diverse and richer set of sentiment-bearing expressions in tweets, including formal and slang words/phrases, not limited to pre-specified syntactic patterns; (ii) instead of associating sentiment with an entire tweet, we assess the target-dependent polarity of each sentiment expression. The polarity of sentiment expression is determined by the nature of its target; (iii) we provide a novel formulation of assigning polarity to a sentiment expression as a constrained optimization problem over the tweet corpus. Experiments conducted on two domains, tweets mentioning movie and person entities, show that our approach improves accuracy in comparison with several baseline methods, and that the improvement becomes more prominent with increasing corpus sizes.

We consider active, semi-supervised learning in an offline transductive setting. We show that a previously proposed error bound for active learning on undirected weighted graphs can be generalized by replacing graph cut with an arbitrary symmetric submodular function. Arbitrary non-symmetric submodular functions can be used via symmetrization. Different choices of submodular functions give different versions of the error bound that are appropriate for different kinds of problems. Moreover, the bound is deterministic and holds for adversarially chosen labels. We show exactly minimizing this error bound is NP-complete. However, we also introduce for any submodular function an associated active semi-supervised learning method that approximately minimizes the corresponding error bound. We show that the error bound is tight in the sense that there is no other bound of the same form which is better. Our theoretical results are supported by experiments on real data.

In this paper, we present an alternative to the Turing Test that has some conceptual and practical advantages. A Winograd schema is a pair of sentences that differ only in one or two words and that contain a referential ambiguity that is resolved in opposite directions in the two sentences. We have compiled a collection of Winograd schemas, designed so that the correct answer is obvious to the human reader, but cannot easily be found using selectional restrictions or statistical techniques over text corpora. A contestant in the Winograd Schema Challenge is presented with a collection of one sentence from each pair, and required to achieve human-level accuracy in choosing the correct disambiguation.