Vanessa Murdock

The Benchmark as a Research Catalyst: Charting the Progress of Geo-prediction for Social Multimedia

Benchmarks have the power to bring research communities together to focus on specific research challenges. They drive research forward by making it easier to systematically compare and contrast new solutions, and evaluate their performance with respect to the existing state of the art. In this chapter, we present a retrospective on the Placing Task, a yearly challenge offered by the MediaEval Multimedia Benchmark. The Placing Task, launched in 2010, is a benchmarking task that requires participants to develop algorithms that automatically predict the geolocation of social multimedia (videos and images). This chapter covers the editions of the Placing Task offered in 2010–2013, and also presents an outlook onto 2014. We present the formulation of the task and the task dataset for each year, tracing the design decisions that were made by the organizers, and how each year built on the previous year. Finally, we provide a summary of future directions and challenges for multimodal geolocation, and concluding remarks on how benchmarking has catalyzed research progress in the research area of geolocation prediction for social multimedia.

Geographic Information Retrieval: Progress and Challenges in Spatial Search of Text

Significant amounts of information available today contain references to places on earth. Traditionally such information has been held as structured data and was the concern of Geographic Information Systems (GIS). However, increasing amounts of data in the form of unstructured text are available for indexing and retrieval that also contain spatial references. This monograph describes the field of Geographic Information Retrieval (GIR) that seeks to develop spatially-aware search systems and support user’s geographical information needs. Important concepts with respect to storing, querying and analysing geographical information in computers are introduced, before user needs and interaction in the context of GIR are explored. The task of associating documents with coordinates, prior to their indexing and ranking forms the core of any GIR system, and different approaches and their implications are discussed. Evaluating the resulting systems and their components, and different paradigms for doing so continue to be an important area of research in GIR and are illustrated through several examples. The monograph provides an overview of the research field, and in so doing identifies key remaining research challenges in GIR.

Fifth workshop on exploiting semantic annotations in information retrieval: ESAIR''12)

There is an increasing amount of structure on the Web as a result of modern Web languages, user tagging and annotation, emerging robust NLP tools, and an ever growing volume of linked data. These meaningful, semantic, annotations hold the promise to significantly enhance information access, by enhancing the depth of analysis of todays systems. Currently, we have only started exploring the possibilities and only begin to understand how these valuable semantic cues can be put to fruitful use. To complicate matters, standard text search excels at shallow information needs expressed by short keyword queries, and here semantic annotation contributes very little, if anything. The main questions for the workshop are how to leverage the rich context currently available, especially in a mobile search scenario, giving powerful new handles to exploit semantic annotations. And how can we fruitfully combine information retrieval and semantic web approaches, and for the first time work actively toward a unified view on exploiting semantic annotations.

Second Workshop on Search and Exploration of X-Rated Information (SEXI'16): WSDM Workshop Summary

Adult content is pervasive on the web, has been a driving factor in the adoption of the Internet medium, and is responsible for a significant fraction of traffic and revenues, yet rarely attracts attention in research. The research questions surrounding adult content access behaviors are unique, and interesting and valuable research in this area can be done ethically. WSDM 2016 features a half day workshop on Search and Exploration of X-Rated Information (SEXI) for information access tasks related to adult content. While the scope of the workshop remains broad, special attention is devoted to the privacy and security issues surrounding adult content by inviting keynote speakers with extensive experience on these topics. The recent release of the personal data belonging to customers of the adult dating site Ashley Madison provides a timely context for the focus on privacy and security.

Dynamic location models

Location models built on social media have been shown to be an important step toward understanding places in queries. Current search technology focuses on predicting broad regions such as cities. Hyperlocal scenarios are important because of the increasing prevalence of smartphones and mobile search and recommendation. Users expect the system to recognize their location and provide information about their immediate surroundings. In this work we propose an algorithm for constructing hyperlocal models of places that are as small as half a city block. We show that Dynamic Location Models (DLMs) are computationally efficient, and provide better estimates of the language models of hyperlocal places than the standard method of segmenting the globe into approximately equal grid squares. We evaluate the models using a repository of 25 million geotagged public images from Flickr. We show that the indexes produced by DLMs have a larger vocabulary, and smaller average document length than their fixed grid counterparts, for indexes with an equivalent number of locations. This produces location models that are more robust to retrieval parameters, and more accurate in predicting locations in text.

Inter-Category Variation in Location Search

When searching for place entities such as businesses or points of interest, the desired place may be close (finding the nearest ATM) or far away (finding a hotel in another city). Understanding the role of distance in predicting user interests can guide the design of location search and recommendation systems. We analyze a large dataset of location searches on GPS-enabled mobile devices with 15 location categories. We model user-location distance based on raw geographic distance (kilometers) and intervening opportunities (nth closest). Both models are helpful in predicting user interests, with the intervening opportunity model performing somewhat better. We find significant inter-category variation. For instance, the closest movie theater is selected in 17.7% of cases, while the closest restaurant in only 2.1% of cases. Overall, we recommend taking category information into account when modeling location preferences of users in search and recommendation systems.

SIGIR 2014 workshop on temporal, social and spatially-aware information access (#TAIA2014)

Spatial and temporal context are increasingly important as users rely more on mobile devices to access information on the Web. Although information access applications are becoming more context-savvy, users’ expectations are far ahead of current capabilities. For example, users expect a given application to understand the nature of their current immediate surroundings, while many systems have trouble drawing an accurate map of a city, or assigning a geographic and temporal scope to a web document. Successfully incorporating spatial and temporal context into the retrieval and user models opens up a universe of hyperlocal scenarios. Users provide an unprecedented volume of detailed, and continuously updated information about where they are, what they are doing, who they are with, and what they are thinking and feeling about their current activities. The provision of this stream creates an informal contract between the user and the information access application that the user will provide the information, but the application must provide results that are contextually relevant. Many of the research questions about how to understand and employ user context have yet to be answered. We bring together practitioners and researchers, in a program centered around short papers, keynote speakers, and discussion of recent breakthroughs and challenges in spatial and temporal information access, from algorithmic and architectural perspectives.

Two Ways of Thinking About Where People Go

In this talk we present two historical models of human migration from the 19th and 20th centuries, and discuss how they apply to location data on the Web, in the 21st Century.

Location in Search

As users turn increasingly to handheld devices to find information, the research community has focused on real-time location signals (GPS signals) to improve search engine effectiveness. Location signals have been investigated for predicting businesses the user will frequent[3], assigning geographic coordinates to media files[1], and to improve mobile search ranking[2]. While the increased focus on real-time user location has produced excellent research, there remains a gap between the capabilities being developed in the research community, and the capabilities being developed by commercial search engines. The core of this discrepancy between the advances in research and advances in industry is understanding the users location. The vast majority of research on user location assumes that the users location is known, because the user has provided a GPS signal. For many systems, there is no GPS signal available. The user may choose not enable it, or the system chooses not to prompt the user for the location because doing so degrades the user experience. For these interactions, the system relies on the users IP address for location information. Further, much of the current research uses public geocoded data such as Foursquare (http://www.foursquare.com visited June 2015), and Twitter (http://www.twitter.com visited June 2015). These data are an incomplete picture of places a user may visit, and are potentially biased in their representation of actual users. The information contained in these data is not the same type of information typically available to a commercial search engine. In this talk we discuss gaps between current research on location, and industry advances in using location signals to improve search results. We focus on user location as one example of a gap between research and development.

Report on the fifth workshop on exploiting semantic annotations in information retrieval (ESAIR'12)

There is an increasing amount of structure on the web as a result of modern web languages, user tagging and annotation, emerging robust NLP tools, and an ever growing volume of linked data. These meaningful, semantic, annotations hold the promise to significantly enhance information access, by enhancing the depth of analysis of todays systems. Currently, we have only started exploring the possibilities and only begin to understand how these valuable semantic cues can be put to fruitful use. To complicate matters, standard text search excels at shallow information needs expressed by short keyword queries, and here semantic annotation contributes very little, if anything. The main questions for the workshop are how to leverage the rich context currently available, especially in a mobile search scenario, giving powerful new handles to exploit semantic annotations. And how can we fruitfully combine information retrieval and knowledge intensive approaches, and for the first time work actively toward a unified view on exploiting semantic annotations. There was a strong feeling that we made substantial progress. Specifically, each of the breakout groups contributed to our understanding of the way forward. First, there is a need for further integration of symbolic and statistical methods with each adopting parts of the others strengths, by focusing on types of annotations that are informed by and meaningful for the task at hand, and relying on automatic information extraction and annotation based on web scale observations. Second, the discussion contributed to the creation of a concrete shared corpus with state of the art semantic annotation--in particular a web crawl annotated with Freebase concepts--that will benefit research in this area for years to come.