Sarcasm is a sophisticated form of speech act widely used in online communities. Automatic recognition of sarcasm is, however, a novel task. Sarcasm recognition could contribute to the performance of review summarization and ranking systems. This paper presents SASI, a novel Semi-supervised Algorithm for Sarcasm Identification that recognizes sarcastic sentences in product reviews. SASI has two stages: semi-supervised pattern acquisition, and sarcasm classification. We experimented on a data set of about 66000 Amazon reviews for various books and products. Using a gold standard in which each sentence was tagged by 3 annotators, we obtained precision of 77% and recall of 83.1% for identifying sarcastic sentences. We found some strong features that characterize sarcastic utterances. However, a combination of more subtle pattern-based features proved more promising in identifying the various facets of sarcasm. We also speculate on the motivation for using sarcasm in online communities and social networks.

Online social media often highlight content that is highly rated by neighbors in a social network. For the news aggregator Digg, we use a stochastic model to distinguish the effect of the increased visibility from the network from how interesting content is to users. We find a wide range of interest, and distinguish stories primarily of interest to users in the network from those of more general interest to the user community. This distinction helps predict a story's eventual popularity from users' early reactions to the story.

Given a set of reviews of products or merchants from a wide range of authors and several reviews websites, how can we measure the true quality of the product or merchant?  How do we remove the bias of individual authors or sources?  How do we compare reviews obtained from different websites, where ratings may be on different scales (1-5 stars, A/B/C, etc.)?  How do we filter out unreliable reviews to use only the ones with ``star quality''?  Taking into account these considerations, we analyze data sets from a variety of different reviews sites (the first paper, to our knowledge, to do this). These data sets include 8 million product reviews and 1.5 million merchant reviews. We explore statistic- and heuristic- based models for estimating the true quality of a product or merchant, and compare the performance of these estimators on the task of ranking pairs of objects.  We also apply the same models to the task of using Netflix ratings data to rank pairs of movies, and discover that the performance of the different models is surprisingly similar on this data set.

Over the past decade, we have been engaged in an extensive research effort to build virtual humans and applications that use them.  Building a virtual human might be considered the quintessential AI problem, because it brings together many of the key features, such as autonomy, natural communication, sophisticated reasoning and behavior, that distinguish AI systems.  This paper describes major virtual human systems we have built and important lessons we have learned along the way.

Probabilistic matrix factorization (PMF) is a powerful method for modeling data associated with pairwise relationships, finding use in collaborative filtering, computational biology, and document analysis, among other areas. In many domains, there is additional information that can assist in prediction. For example, when modeling movie ratings, we might know when the rating occurred, where the user lives, or what actors appear in the movie. It is difficult, however, to incorporate this side information into the PMF model. We propose a framework for incorporating side information by coupling together multiple PMF problems via Gaussian process priors. We replace scalar latent features with functions that vary over the space of side information. The GP priors on these functions require them to vary smoothly and share information. We successfully use this new method to predict the scores of professional basketball games, where side information about the venue and date of the game are relevant for the outcome.

Painters write about their what artists say about their own work, using motivations; photographers, about details of the concept mapping as a conceptual capture tool (Eskridge et.

In this paper we describe the production and consumption of linked data in the scenario of the Italian news agency ANSA portal. The goal of the use-case is to provide viewers of a news item with background information and links to related news articles contained on the portal. This information enrichment process is entity-based: ANSA news archive is analyzed using Name Entity Recognition, and each detected entity is annotated with a unique identifier. These identifiers are obtained using the Entity Name Server developed within the scope of the OKKAM European project. Subsequently the news are published on the portal using RDFa and linked to a semantic search engine that provides background information harvested from sources such as DBpedia and links to additional news sources. The presented project has the potential to contribute to Linked Data by creating and publishing a large quantity of entities and assertions about them coming from the ANSA news archive.

While recommender systems can greatly enhance the user experience, the entry barriers in terms of data acquisition are very high, making it hard for new service providers to compete with existing recommendation services. This paper proposes to build open recommender systems which can utilise Linked Data to mitigate the new-user, new-item and sparsity problems of collaborative recommender systems. We describe how to aggregate data about object centred sociality from different sources and how to process it for collaborative recommendation. To demonstrate the validity of our approach, we augment the data from a closed collaborative music recommender system with Linked Data, and significantly improve its precision and recall.

In this paper, we describe our initial experiences using a mobile robot as a teaching aid in a stage movement class, taught in the Performing Arts Department of Washington University in St. Louis. The robot participated in a number of exercises, intended to teach the fundamentals of movement, and interacted closely with human acting students. We describe these exercises, what they are designed to teach the students, and discuss how using a robot as a teaching aid can enhance the students' experience. We describe two classes in which a robot participated, one under tele-operation and one fully autonomously, and discuss both the students' reaction to the robots, and our subjective evaluations of the systems success.

Anticipating the actions of others is key to coordinating joint activities. We propose the notion of anticipatory action and perception for for robots acting with humans. We describe four systems in which anticipation has been modeled for human-robot interaction; two in a teamwork setting, and two in a human-robot joint performance setting. In evaluating the effects of anticipatory agent activity, we find in one study that anticipation aids in team efficiency, as well as in the perceived commitment of the robot to the team and its contribution to the team's fluency and success. In another study we see anticipatory action and perception affect the human partner's sense of team fluency, the team's improvement over time, the robot’s contribution to the efficiency and fluency, the robot's intelligence, and the robot’s adaptation to the task. We also find that subjects working with the anticipatory robot attribute more human qualities to the robot, such as gender and intelligence.