In this study, we examine human social interactions within virtual worlds and address the question of how group interactions are affected by the game environment. To investigate this problem, we introduced a set of conversational agents into the social environment of Second Life, a massively multi-player online environment that allows users to construct and inhabit their own 3D world. Our agents were created to be sufficiently lifelike to casual observers, so as not to perturb neighboring social interactions. Using our partitioning algorithm, we separated continuous public chat logs from each region into separate conversations which were used to construct a social network of the participants. Unlike many groups formed in communities and workplaces, groups in Second Life can be rapidly-forming (arising from few interactions), persistent (remaining stable over a long period), and are less affected by socio-cultural influences. In this paper, we analyze regional differences in Second Life by measuring characteristics of the network as a whole, determined from the statistics mined from public conversations in the virtual world, rather than focusing on egocentric actors and their attributes.

Using comment information available from Digg we define a co-participation network between users. We focus on the analysis of this implicit network, and study the behavioral characteristics of users. We use the comment data and social network derived features to predict the popularity of online content linked at Digg using a classification and regression framework. We also compare network properties of our co-participation network to a previously defined reply-answer network on news forums.

Textual sentiment classifiers classify texts into a fixed number of affective classes, such as positive, negative or neutral sentiment, or subjective versus objective information. It has been observed that sentiment classifiers suffer from a lack of generalization capability: a classifier trained on a certain domain generally performs worse on data from another domain. This phenomenon has been attributed to domain-specific affective vocabulary. In this paper, we propose a voting-based thresholding approach, which calibrates a number of existing single-domain classifiers with respect to sentiment data from a new domain. The approach presupposes only a small amount of annotated data from the new domain. We evaluate three criteria for estimating thresholds, and discuss the ramifications of these criteria for the trade-off between classifier performance and manual annotation effort.

Many researchers conducted studies on extracting relevant information from web documents. However, there are few studies on extracting serendipitous information. We propose methods to discover unexpected information from Wikipedia by using its network structure, for example, the distance between two categories. We evaluated two methods: a classification-based method using support vector machines (SVMs), and a ranking-based method using regression. We demonstrate advantages of regression over classification.

The Web has become an important information repository; often it is the first source a person turns to with an informa-tion need. One common way to search the Web is with a search engine. However, it is not always easy for people to find what they are looking for with keyword search, and at times the desired information may not be readily available online. An alternative, facilitated by the rise of social media, is to pose a question to one‟s online social network. In this paper, we explore the pros and cons of using a social net-working tool to fill an information need, as compared with a search engine. We describe a study in which 12 participants searched the Web while simultaneously posing a question on the same topic to their social network, and we compare the results they found by each method.

We present a new similarity measure tailored to posts in an online forum. Our measure takes into account all the available information about user interest and interaction — the content of posts, the threads in the forum, and the author of the posts. We use this post similarity to build a similarity between users, based on principal coordinate analysis. This allows easy visualization of the user activity as well. Similarity between users has numerous applications, such as clustering or classification. We show that including the author of a post in the post similarity has a smoothing effect on principal coordinate projections. We demonstrate our method on real data drawn from an internal corporate forum, and compare our results to those given by a standard document classification method. We conclude our method gives a more detailed picture of both the local and global network structure.

This paper addresses the problem of automatically generating domain-specific sentiment clues. The main idea is to bootstrap from a small seed set and generate new clues by using dependencies and collocation information between sentiment clues and sentence-level topics that would be a primary subject of sentiment expression (e.g., event, company, and person). The experiments show that the aggregated clues are effective for sentiment classification.

We propose a new method of recommending questions to answerers so as to suit the answerers’ knowledge and interests in User-Interactive Question Answering (QA) communities. A question recommender can help answerers select the questions that interest them. This increases the number of answers, which will activate QA communities. An effective question recommender should satisfy the following three requirements: First, its accuracy should be higher than the existing category-based approach; more than 50% of answerers select the questions to answer according a fixed system of categories. Second, it should be able to recommend unanswered questions because more than 2,000 questions are posted every day. Third, it should be able to support even those people who have never answered a question previously, because more than 50% of users in current QA communities have never given any answer. To achieve an effective question recommender, we use question histories as well as the answer histories of each user by combining collaborative filtering schemes and content-base filtering schemes. Experiments on real log data sets of a famous Japanese QA community, Oshiete goo, show that our recommender satisfies the three requirements.

Social annotation has become a popular manner for web users to manage and share their information and interests. While users' interests vary with time, tag correlation also changes from users' perspectives. In this work, we explore four methods for estimating temporal correlation between social tags and detect if a long-term trend emerges from the history of temporal correlation between two tags. Three types of trends are specified: steadily-shifting, stabilizing, and cyclic. To compare the results of the four estimation methods, an indirect evaluation is realized by applying detected trends to tag recommendation.

The American Football betting market provides a particularly attractive domain to study the nexus between public sentiment and the wisdom of crowds. In this paper, we present the first substantial study of the relationship between the NFL betting line and public opinion expressed in blogs and microblogs (Twitter). We perform a large-scale study of four distinct text streams: LiveJournal blogs, RSS blog feeds captured by Spinn3r, Twitter, and traditional news media. Our results show interesting disparities between the first and second halves of each season. We present evidence showing usefulness of sentiment on NFL betting. We demonstrate that a strategy betting roughly 30 games per year identified winner roughly 60% of the time from 2006 to 2009, well beyond what is needed to overcome the bookie's typical commission(53%).