Many IR collections contain forbidden documents (F-docs), i.e. documents that should not be retrieved to the searcher. In an ideal scenario F-docs are clearly flagged, hence the ranker can filter them out, guaranteeing that no F-doc will be exposed. However, in real-world scenarios, filtering algorithms are prone to errors. Therefore, an IR evaluation system should also measure filtering quality in addition to ranking quality. Typically, filtering is considered as a classification task and is evaluated independently of the ranking quality. However, due to the mutual affinity between the two, it is desirable to evaluate ranking quality while filtering decisions are being made. In this work we propose nDCGf, a novel extension of the nDCGmin metric[14], which measures both ranking and filtering quality of the search results. We show both theoretically and empirically that while nDCGmin is not suitable for the simultaneous ranking and filtering task, nDCGf is a reliable metric in this case.

In this study we address the problem of identifying the purchase-state of users, based on product-related questions they ask on an eCommerce website. We differentiate between questions asked before buying a product (pre-purchase) and after (post-purchase). At first, we study the ambiguity that exists in purchase-states' definition, and then investigate the linguistic characteristics of the questions in each state. We analyze the discrepancy between the language models of pre- and post-purchase questions, and offer two classification schemes for this task, both outperform human judgments. We additionally show the effectiveness of our classification models in improving real world applications for both consumers and sellers.

Associating type to locations can be used to enrich maps and can serve a plethora of geospatial applications. An automatic method to do so could make the process less expensive in terms of human labor, and faster to react to changes. In this paper we study the problem of Geosocial Location Classification, where the type of a site, e.g., a building, is discovered based on social-media posts. Our goal is to correctly associate a set of messages posted in a small radius around a given location with the corresponding location type, e.g., school, church, restaurant or museum. We explore two approaches to the problem: (a) a pipeline approach, where each message is first classified, and then the location associated with the message set is inferred from the separate message labels; and (b) a joint approach where the messages are simultaneously processed to yield the desired location type. We tested the two approaches over a dataset of geotagged tweets. Our results demonstrate the superiority of the joint approach.

Community question-answering (CQA) has been established as a prominent web service enabling users to post questions and get answers from the community. Product Question Answering (PQA) is a special CQA framework where questions are asked (and are answered) in the context of a specific product. Naturally, humorous questions are integral part of such platforms, especially as some products attract humor due to their unreasonable price, their peculiar functionality, or in cases that users emphasize their critical point-of-view through humor. Detecting humorous questions in such systems is important for sellers, to better understand user engagement with their products. It is also important to signal users about flippancy of humorous questions, and that answers for such questions should be taken with a grain of salt.

This article investigates the problem of geosocial similarity among users of online social networks, based on the locations of their activities (e.g., posting messages or photographs). Finding pairs of geosocially similar users or detecting that two sets of locations (of activities) belong to the same user has important applications in privacy protection, recommendation systems, urban planning, and public health, among others. It is explained and shown empirically that common distance measures between sets of locations are inadequate for determining geosocial similarity. Two novel distance measures between sets of locations are introduced. One is the mutually nearest distance that is based on computing a matching between two sets. The second measure uses a quad-tree index. It is highly scalable but incurs the overhead of creating and maintaining the index. Algorithms with optimization techniques are developed for computing the two distance measures and also for finding the k -most-similar users of a given one. Extensive experiments, using geotagged messages from Twitter, show that the new distance measures are both more accurate and more efficient than existing ones.

In this paper, we study multi-click queries - queries for which more than one click is performed by the same user within the same query session. Such queries may reflect a more complex information need, which leads the user to examine a variety of results. We present a comprehensive analysis that reveals unique characteristics of multi-click queries, in terms of their syntax, lexical domains, contextual properties, and returned search results page. We also show that a basic classifier for predicting multi-click queries can reach an accuracy of 75% over a balanced dataset. We discuss the implications of our findings for the design of Web search tools.

In the web, page creators often compete for their ranking on relevant search queries, as high ranking attracts users and may lead to increased revenues. The positive effect of this competition is that it encourages page owners to improve their content. However, some techniques used for this improvement, such as keyword stuffing, are considered harmful. Current search engine literature largely ignores the interplay between the retrieval system and the pages' content evolvement. This paper studies the above phenomenon.

Although online communities have become popular both on the web and within enterprises, many of them often experience low levels of activity and engagement from their members. Previous studies identified the important role of community leaders in maintaining the health and vitality of their communities. One of their key means for doing so is by contributing relevant content to the community. In this paper, we study the effects of recommending social media content on enterprise community leaders. We conducted a large-scale user survey with four recommendation rounds, in which community leaders indicated their willingness to share social media items with their communities. They also had the option to instantly share these items. Recommendations were generated based on seven types of community interest profiles that were member-based, content-based, or hybrid. Our results attest that providing content recommendations to leaders can help uplift activity within their communities.

With mobile devices, web search is no longer limited to specific locations. People conduct search from practically anywhere, including at home, at work, when traveling and when on vacation. How should this influence search tools and web services? In this paper, we argue that information needs are affected by the familiarity of the environment. To formalize this idea, we propose a new contextualization model for activities on the web. The model distinguishes between a search from a familiar place (F-search) and a search from an unfamiliar place (U-search). We formalize the notion of familiarity, and propose a method to identify familiar places. An analysis of a query log of millions of users, demonstrates the differences between search activities in familiar and in unfamiliar locations. Our novel take on search contextualization has the potential to improve web applications, such as query autocompletion and search personalization.

Recently, there is a rapid growth in the use of microblogs, such as Twitter, and of social networks, such as Instagram, to publish geo-tagged posts that indicate the location of the user at the time when the message is sent. This provides abundant geospatial data that can be analyzed to understand the behavior of masses of people, in particular in urban. Such analysis can improve and facilitate the work of urban planners and of policy makers, e.g., when deciding where to add transportation routes or public institutes. In this demonstration, we present a system that utilizes geo-tagged posts to discover places that were jointly visited by many people. We present the management and the analysis of the data, to illustrate the feasibility of the approach and to indicate new research questions in this domain.

Online communities within the enterprise offer their leaders an easy and accessible way to attract, engage, and influence others. Our research studies the recommendation of social media content to leaders (owners) of online communities within the enterprise. We developed a system that suggests to owners new content from outside the community, which might interest the community members. As online communities are taking a central role in the pervasion of social media to the enterprise, sharing such recommendations can help owners create a more lively and engaging community. We compared seven different methods for generating recommendations, including content-based, member-based, and hybridization of the two. For member-based recommendations, we experimented with three groups: owners, active members, and regular members. Our evaluation is based on a survey in which 851 community owners rated a total of 8,218 recommended content items. We analyzed the quality of the different recommendation methods and examined the effect of different community characteristics, such as type and size.

Offline map matching is a process of associating a sequence of GPS location readings measured with a device held by a traveling user, to the real-world roads that were presumably traveled by the user. The main goals in map matching are (1) to provide an association which is as accurate as possible with respect to actual traveled roads, and (2) to compute the matching as efficiently as possible. We describe our implementation of a map matching algorithm that enables parallel computation of the matching, being developed as part of the ACM SIGSPATIAL CUP 2012 contest, and we present the results of an experimental evaluation over the data of the contest. We show that our algorithm is efficient and robust in the sense that it maintains a high level of accuracy even when the sampling rate is low.