Sheila Kinsella

Searching and browsing Linked Data with SWSE: The Semantic Web Search Engine

In this paper, we discuss the architecture and implementation of the Semantic Web Search Engine (SWSE). Following traditional search engine architecture, SWSE consists of crawling, data enhancing, indexing and a user interface for search, browsing and retrieval of information; unlike traditional search engines, SWSE operates over RDF Web data - loosely also known as Linked Data - which implies unique challenges for the system design, architecture, algorithms, implementation and user interface. In particular, many challenges exist in adopting Semantic Web technologies for Web data: the unique challenges of the Web - in terms of scale, unreliability, inconsistency and noise - are largely overlooked by the current Semantic Web standards. Herein, we describe the current SWSE system, initially detailing the architecture and later elaborating upon the function, design, implementation and performance of each individual component. In so doing, we also give an insight into how current Semantic Web standards can be tailored, in a best-effort manner, for use on Web data. Throughout, we offer evaluation and complementary argumentation to support our design choices, and also offer discussion on future directions and open research questions. Later, we also provide candid discussion relating to the difficulties currently faced in bringing such a search engine into the mainstream, and lessons learnt from roughly six years working on the Semantic Web Search Engine project.

I'm eating a sandwich in Glasgow: modeling locations with tweets

Social media such as Twitter generate large quantities of data about what a person is thinking and doing in a particular location. We leverage this data to build models of locations to improve our understanding of a users geographic context. Understanding the users geographic context can in turn enable a variety of services that allow us to present information, recommend businesses and services, and place advertisements that are relevant at a hyper-local level. In this paper we create language models of locations using coordinates extracted from geotagged Twitter data. We model locations at varying levels of granularity, from the zip code to the country level. We measure the accuracy of these models by the degree to which we can predict the location of an individual tweet, and further by the accuracy with which we can predict the location of a user. We find that we can meet the performance of the industry standard tool for predicting both the tweet and the user at the country, state and city levels, and far exceed its performance at the hyper-local level, achieving a three- to ten-fold increase in accuracy at the zip code level.

Using Naming Authority to Rank Data and Ontologies for Web Search

The focus of web search is moving away from returning relevant documents towards returning structured data as results to user queries. A vital part in the architecture of search engines are link-based ranking algorithms, which however are targeted towards hypertext documents. Existing ranking algorithms for structured data, on the other hand, require manual input of a domain expert and are thus not applicable in cases where data integrated from a large number of sources exhibits enormous variance in vocabularies used. In such environments, the authority of data sources is an important signal that the ranking algorithm has to take into account. This paper presents algorithms for prioritising data returned by queries over web datasets expressed in RDF. We introduce the notion of naming authority which provides a correspondence between identifiers and the sources which can speak authoritatively for these identifiers. Our algorithm uses the original PageRank method to assign authority values to data sources based on a naming authority graph, and then propagates the authority values to identifiers referenced in the sources. We conduct performance and quality evaluations of the method on a large web dataset. Our method is schema-independent, requires no manual input, and has applications in search, query processing, reasoning, and user interfaces over integrated datasets.

Topic classification in social media using metadata from hyperlinked objects

Social media presents unique challenges for topic classification, including the brevity of posts, the informal nature of conversations, and the frequent reliance on external hyperlinks to give context to a conversation. In this paper we investigate the usefulness of these external hyperlinks for determining the topic of an individual post. We focus specifically on hyperlinks to objects which have related metadata available on the Web, including Amazon products and YouTube videos. Our experiments show that the inclusion of metadata from hyperlinked objects in addition to the original post content improved classifier performance measured with the F-score from 84% to 90%. Further, even classification based on object metadata alone outperforms classification based on the original post content.

Navigating and Annotating Semantically-Enabled Networks of People and Associated Objects

Social spaces such as blogs, wikis and online social networking sites are enabling the formation of online communities where people are linked to each other through direct profile connections and also through the content items that they are creating, sharing and tagging. As these spaces become bigger and more distributed, more intuitive ways of navigating the associated information become necessary. The Semantic Web aims to link identifiable objects to each other and to textual strings via relationships and attributes respectively, and provides a platform for gathering diverse information from heterogeneous sources and performing operations on such linked data. In this paper, we will demonstrate how this linked semantic data can provide an enhanced view of the activity in a social network, and how the Galaxy tool described in this work can augment objects from social spaces, by highlighting related people and objects, and suggesting relevant sources of knowledge.

An Interactive Map of Semantic Web Ontology Usage

Publishing information on the Semantic Web using common formats enables data to be linked together, integrated and reused. In order to fully leverage the potential for interlinking data by reusing existing schemas, an intuitive way of viewing current usage of RDF vocabularies is required. We present a system which allows a user to view the most frequently occurring name spaces and classes in a large Semantic Web dataset, and the main linkage patterns that exist between them. Users can select a namespace of interest in order to examine usage of a particular ontology, and see how it is being combined with other vocabularies.

From Web 1.0 to Web 2.0 and back -: how did your grandma use to tag?

We consider the applicability of terms extracted from anchortext as a source of Web page descriptions in the form of tags. With a relatively simple and easy-to-use method, we show that anchortext significantly overlaps with tags obtained from the popular tagging portal del.icio.us. Considering the size and diversity of the user community potentially involved in social tagging, this observation is rather surprising. Furthermore, we show by an evaluation using human-created relevance assessments the general suitability of the anchortext tag generation in terms of user-perceived precision values. The awareness of this easy-to-obtain source of tags could trigger the rise of new tagging portals pushed by this automatic bootstrapping process or be applied in already existing portals to increase the number of tags per page by merely looking at the anchortext which exists anyway.

Improving categorisation in social media using hyperlinks to structured data sources

Social media presents unique challenges for topic classification, including the brevity of posts, the informal nature of conversations, and the frequent reliance on external hyperlinks to give context to a conversation. In this paper we investigate the usefulness of these external hyperlinks for categorising the topic of individual posts. We focus our analysis on objects that have related metadata available on the Web, either via APIs or as Linked Data. Our experiments show that the inclusion of metadata from hyperlinked objects in addition to the original post content significantly improved classifier performance on two disparate datasets. We found that including selected metadata from APIs and Linked Data gave better results than including text from HTML pages. We investigate how this improvement varies across different topics. We also make use of the structure of the data to compare the usefulness of different types of external metadata for topic classification in a social media dataset.

Using hyperlinks to enrich message board content with linked data

Since social media sites have existed, a major element of the conversations which take place on them has been links to external websites. Users share videos or photos they have seen, point to products or movies they are interested in, and use external articles as a reference in discussions. As websites publish more structured and machine-readable data, notably in RDF, an increasing number of the links posted to social media sites do not just point to a webpage but are also associated with a structured data source. The integration of such external data can give us an enhanced insight into the conversation, both for analysing communities and for building applications. This approach can be applied to any online social space, but in this paper we present the use-case of enriching bulletin boards. We investigate the hyperlinks posted on a message board over a 10 year period and show how the external structured information related to these links has grown. We use data aggregated from several external sites providing RDF data or APIs to show how enriching forums with external data can provide us with enhanced insight into online conversation. We discuss potential applications of this approach, for message boards and for social media in general.

Searching and Browsing Linked Data with SWSE

Web search engines such as Google, Yahoo! MSN/Bing, and Ask are far from the consummate Web search solution: they do not typically produce direct answers to queries but instead typically recommend a selection of related documents from the Web. We note that in more recent years, search engines have begun to provide direct answers to prose queries matching certain common templates—for example, “population of china” or “12 euro in dollars”—but again, such functionality is limited to a small subset of popular user queries. Furthermore, search engines now provide individual and focused search interfaces over images, videos, locations, news articles, books, research papers, blogs, and real-time social media—although these tools are inarguably powerful, they are limited to their respective domains.