This work describes an answer ranking engine for non-factoid questions built using a large online community-generated question-answer collection (Yahoo! Answers). We show how such collections may be used to effectively set up large supervised learning experiments. Furthermore we investigate a wide range of feature types, some exploiting NLP processors, and demonstrate that using them in combination leads to considerable improvements in accuracy. 1

There are many on-line settings in which users publicly express opinions. A number of these offer mechanisms for other users to evaluate these opinions; a canonical example is Amazon.com, where reviews come with annotations like “26 of 32 people found the following review helpful. ” Opinion evaluation appears in many off-line settings as well, including market research and political campaigns. Reasoning about the evaluation of an opinion is fundamentally different from reasoning about the opinion itself: rather than asking, “What did Y think of X?”, we are asking, “What did Z think of Y’s opinion of X? ” Here we develop a framework for analyzing and modeling opinion evaluation, using a large-scale collection of Amazon book reviews as a dataset. We find that the perceived helpfulness of a review depends not just on its content but also but also in subtle ways on how the expressed evaluation relates to other evaluations of the same product. As part of our approach, we develop novel methods that take advantage of the phenomenon of review “plagiarism ” to control for the effects of text in opinion evaluation, and we provide a simple and natural mathematical model consistent with our findings. Our analysis also allows us to distinguish among the predictions of competing theories from sociology and social psychology, and to discover unexpected differences in the collective opinion-evaluation behavior of user populations from different countries.

Social media sites (e.g., Flickr, YouTube, and Facebook) are a popular distribution outlet for users looking to share their experiences and interests on the Web. These sites host substantial amounts of user-contributed materials (e.g., photographs, videos, and textual content) for a wide variety of real-world events of different type and scale. By automatically identifying these events and their associated user-contributed social media documents, which is the focus of this paper, we can enable event browsing and search in state-of-the-art search engines. To address this problem, we exploit the rich “context ” associated with social media content, including user-provided annotations (e.g., title, tags) and automatically generated information (e.g., content creation time). Using this rich context, which includes both textual and non-textual features, we can define appropriate document similarity metrics to enable online clustering of media to events. As a key contribution of this paper, we explore a variety of techniques for learning multi-feature similarity metrics for social media documents in a principled manner. We evaluate our techniques on large-scale, realworld datasets of event images from Flickr. Our evaluation results suggest that our approach identifies events, and their associated social media documents, more effectively than the state-of-the-art strategies on which we build.

Abstract. Online tools for collaboration and social platforms have become omnipresent in Web-based environments. Interests and skills of people evolve over time depending in performed activities and joint collaborations. We believe that ranking models for recommending experts or collaboration partners should not only rely on profiles or skill information that need to be manually maintained and updated by the user. In this work we address the problem of expertise mining based on performed interactions between people. We argue that an expertise mining algorithm must consider a person’s interest and activity level in a certain collaboration context. Our approach is based on the PageRank algorithm enhanced by techniques to incorporate contextual link information. An approach comprising two steps is presented. First, offline analysis of human interactions considering tagged interaction links and second composition of ranking scores based on preferences. We evaluate our approach using an email interaction network. 1

Question answering communities such as Naver and Yahoo! Answers have emerged as popular, and often effective, means of information seeking on the web. By posting questions for other participants to answer, information seekers can obtain specific answers to their questions. Users of popular portals such as Yahoo! Answers already have submitted millions of questions and received hundreds of millions of answers from other participants. However, it may also take hours –and sometime days – until a satisfactory answer is posted. In this paper we introduce the problem of predicting information seeker satisfaction in collaborative question answering communities, where we attempt to predict whether a question author will be satisfied with the answers submitted by the community participants. We present a general prediction model, and develop a variety of content, structure, and community-focused features for this task. Our experimental results, obtained from a largescale evaluation over thousands of real questions and user ratings, demonstrate the feasibility of modeling and predicting asker satisfaction. We complement our results with a thorough investigation of the interactions and information seeking patterns in question answering communities that correlate with information seeker satisfaction. Our models and predictions could be useful for a variety of applications such as user intent inference, answer ranking, interface design, and query suggestion and routing.

Topical blog post retrieval is the task of ranking blog posts with respect to their relevance for a given topic. To improve topical blog post retrieval we incorporate textual credibility indicators in the retrieval process. We consider two groups of indicators: post level (determined using information about individual blog posts only) and blog level (determined using information from the underlying blogs). We describe how to estimate these indicators and how to integrate them into a retrieval approach based on language models. Experiments on the TREC Blog track test set show that both groups of credibility indicators significantly improve retrieval effectiveness; the best performance is achieved when combining them.

Community Question Answering (CQA) has emerged as a popular forum for users to pose questions for other users to answer. Over the last few years, CQA portals such as Naver and Yahoo! Answers have exploded in popularity, and now provide a viable alternative to general purpose Web search. At the same time, the answers to past questions submitted in CQA sites comprise a valuable knowledge repository which could be a gold mine for information retrieval and automatic question answering. Unfortunately, the quality of the submitted questions and answers varies widely- increasingly so that a large fraction of the content is not usable for answering queries. Previous approaches for retrieving relevant and high quality content have been proposed, but they require large amounts of manually labeled data – which

Discussion boards and online forums are important platforms for people to share information. Users post questions or problems onto discussion boards and rely on others to provide possible solutions and such question-related content sometimes even dominates the whole discussion board. However, to retrieve this kind of information automatically and effectively is still a non-trivial task. In addition, the existence of other types of information (e.g., announcements, plans, elaborations, etc.) makes it difficult to assume that every thread in a discussion board is about a question. We consider the problems of identifying question-related threads and their potential answers as classification tasks. Experimental results across multiple datasets demonstrate that our method can significantly improve the performance in both question detection and answer finding subtasks. We also do a careful comparison of how different types of features contribute to the final result and show that non-content features play a key role in improving overall performance. Finally, we show that a ranking scheme based on our classification approach can yield much better performance than prior published methods.

An expert finding system allows a user to type a simple text query and retrieve names and contact information of individuals that possess the expertise expressed in the query. This paper proposes a novel approach to expert finding in large enterprises or intranets by modeling candidate experts (persons), web documents and various relations among them with so-called expertise graphs. As distinct from the stateof-the-art approaches estimating personal expertise through one-step propagation of relevance probability from documents to the related candidates, our methods are based on the principle of multi-step relevance propagation in topicspecific expertise graphs. We model the process of expert finding by probabilistic random walks of three kinds: finite, infinite and absorbing. Experiments on TREC Enterprise Track data originating from two large organizations show that our methods using multi-step relevance propagation improve over the baseline one-step propagation based method in almost all cases.

Readability is a crucial presentation attribute that web summarization algorithms consider while generating a querybaised web summary. Readability quality also forms an important component in real-time monitoring of commercial search-engine results since readability of web summaries impacts clickthrough behavior, as shown in recent studies, and thus impacts user satisfaction and advertising revenue. The standard approach to computing the readability is to first collect a corpus of random queries and their corresponding search result summaries, and then each summary is then judged by a human for its readabilty quality. An average readability score is then reported. This process is time consuming and expensive. Besides, the manual evaluation process can not be used in the real-time summary generation process. In this paper we propose a machine learning approach to the problem. We use the corpus as described above and extract summary features that we think may characterize readability. We then estimate a model (gradient boosted decision tree) that predicts human judgments given the features. This model can then be used in real time to estimate the readability of new (unseen) web search summaries and also be used in the summary generation process. We present results on approximately 5000 editorial judgments collected over the course of a year and show examples where the model predicts the quality well and where it disagrees with human judgments. We compare the results of the model to previous models of readability, most notably Collins-Thompson-Callan, Fog and Flesch-Kincaid, and see that our model shows substantially better correlation with editorial judgments as measured by Pearson’s correlation coefficient. The learning algorithm also provides us with the relative importance of the features used.