Search

Scalable search and retrieval over numerous web document collections distributed across different sites can be achieved by adopting a peer-to-peer (P2P) communication model. Terms and their document frequencies are the main components of text information retrieval and as such need to be computed, aggregated, and distributed throughout the system. This is a challenging problem in the context of unstructured P2P networks, since the local document collections may not reflect the global collection in an accurate way. This might happen due to skews in the distribution of documents to peers. Moreover, central assembly of the total information is not a scalable solution due to the excessive cost of storage and maintenance, and because of issues related to digital rights management. In this paper, we present an efficient hybrid approach for aggregation of document frequencies using a hierarchical overlay network for a carefully selected set of the most important terms, together with gossip-based aggregation for the remaining terms in the collections. Furthermore, we present a cost analysis to compute the communication cost of hybrid aggregation. We conduct experiments on three document collections, in order to evaluate the quality of the proposed hybrid aggregation.

The advent of the World Wide Web has made an enormous amount of information available to everyone and the widespread use of digital equipment enables end-users (peers) to produce their own digital content. This vast amount of information requires scalable data management systems. Peer-to-peer (P2P) systems have so far been well established in several application areas, with file-sharing being the most prominent. The next challenge that needs to be addressed is (more complex) data sharing, management and query processing, thus facilitating the delivery of a wide spectrum of novel data-centric applications to the end-user, while providing high Quality-of-Service. In this paper, we propose a self-organizing P2P system that is capable to identify peers with similar content and intentionally assign them to the same super-peer. During content retrieval, fewer super-peers need to be contacted and therefore efficient similarity search is supported, in terms of reduced network traffic and contacted peers. Our approach increases the responsiveness and reliability of a P2P system and we demonstrate the advantages of our approach using large-scale simulations.

The current approach in web searching, i.e., using centralized search engines, rises issues that question their future applicability: 1) coverage and scalability, 2) freshness, and 3) information monopoly. Performing web search using a P2P architecture that consists of the actual web servers has the potential to tackle those issues. In order to achieve the desired performance and scalability, as well as enhancing search quality relative to centralized search engines, semantic overlay networks (SONS) connecting peers storing semantically related information can be employed. The lack of global content/topology knowledge in a P2P system is the key challenge in forming SONS, and this paper describes an unsupervised approach for decentralized and distributed generation of SONS (DESENT). Through simulations and analytical cost models we verify our claims regarding performance, scalability, and quality.

In this paper, we present work-in-progress of a recently started project that aims at studying the effect of time in recommender systems in the context of social tagging. Despite the existence of previous work in this area, no research has yet made an extensive evaluation and comparison of time-aware recommendation methods. With this motivation, this paper presents results of a study where we focused on understanding (i) "when" to use the temporal information into traditional collaborative filtering (CF) algorithms, and (ii) "how" to weight the similarity between users and items by exploring the effect of different time-decay functions. As the results of our extensive evaluation conducted over five social tagging systems (Delicious, BibSonomy, CiteULike, MovieLens, and Last.fm) suggest, the step (when) in which time is incorporated in the CF algorithm has substantial effect on accuracy, and the type of time-decay function (how) plays a role on accuracy and coverage mostly under pre-filtering on user-based CF, while item-based shows stronger stability over the experimental conditions.

Since innovation plays an important role in the context of food, as evident in how successful chefs, restaurants or cuisines in general evolve over time, we were interested in exploring this dimension from a more virtual perspective. In particular, the paper presents results of a study that was conducted in the context of a large-scale German online food community forum to explore another important dimension of online food recipe production, namely known as online food innovation. The study shows interesting findings and temporal patterns in terms of how online food recipe innovation takes place.

In modern applications, spatial objects are often annotated with textual descriptions, and users are offered the opportunity to formulate spatio-textual queries. The result set of such a query consists of spatio-textual objects ranked according to their distance from a desired location and to their textual relevance to the query. In this context, a challenging problem is how to select a set of at most b keywords to enhance the description of the facilities of a spatial object, in order to make the object appear in the top-k results of as many users as possible. In this paper, we formulate this problem, called Best-terms and we show that it is NP-hard. Hence, we present a baseline algorithm that provides an approximate solution to the problem. Then, we introduce a novel algorithm for keyword selection that greatly improves the efficiency of query processing. By means of a thorough experimental evaluation, we demonstrate the performance gains attained by our approach.

In modern heterogeneous environments, such as mobile, pervasive and ad-hoc networks, architectures based on web services offer an attractive solution for effective communication and inter-operation. In such dynamic and rapidly evolving environments, efficient web service discovery is an important task. Usually this task is based on the input/output parameters or other functional attributes, however this does not guarantee the validity or successful utilization of retrieved web services. Instead, non-functional attributes, such as device power features, computational resources and connectivity status, that characterize the context of both service providers and consumers play an important role to the quality and usability of discovery results. In this paper we introduce context-awareness in web service discovery, enabling the provision of the most appropriate services at the right location and time. We focus on context-based caching and routing for improving web service discovery in a mobile peer-to-peer environment. We conducted a thorough experimental study, using our prototype implementation based on the JXTA framework, while simulations are employed for testing the scalability of the approach. We illustrate the advantages that this approach offers, both by evaluating the context-based cache performance and by comparing the efficiency of location-based routing to broadcast-based approaches.

This paper presents ExperTime, a web-based system for tracking expertise over time. We visualize a person's expertise profile on a timeline, where we detect and characterize changes in the focus or topics of expertise. It is possible to zoom in on a given time period in order to examine the underlying data that is used as supporting evidence. It is also possible to perform visual and quantitative comparison of two arbitrarily selected time periods in a highly interactive environment. We invite profile owners to evaluate and fine-tune their profiles, and to leave feedback.

In this paper, we address the problem of discovering a ranked set of k distinct main objects combined with additional (accessory) objects that best fit the given preferences. This problem is challenging because it considers object combinations of variable size, where objects are combined only if the combination produces a higher score, and thus becomes more preferable to a user. In this way, users can explore overviews of combinations that are more suited to their preferences than single objects, without the need to explicitly specify which objects should be combined. We model this problem as a rank-join problem where each combination is represented by a set of tuples from different relations and we call the respective query eXploratory Top-k Join query. Existing approaches fall short to tackle this problem because they impose a fixed size of combinations, they do not distinguish on combinations based on the main objects or they do not take into account user preferences. We introduce a more efficient bounding scheme that can be used on an adaptation of the rank-join algorithm, which exploits some key properties of our problem and allows earlier termination of query processing. Our experimental evaluation demonstrates the efficiency of the proposed bounding technique.

The trend towards in-memory analytics and CPUs with an increasing number of cores calls for new algorithms that can efficiently utilize the available resources. This need is particularly evident in the case of CPU-intensive query operators. One example of such a query with applicability in data analytics is the skyline query. In this paper, we present APS kyline, a new approach for multicore skyline query processing, which adheres to the partition-execute-merge framework. Contrary to existing research, we focus on the partitioning phase to achieve significant performance gains, an issue largely overlooked in previous work in multicore processing. In particular, APS kyline employs an angle-based partitioning approach, which increases the degree of pruning that can be achieved in the execute phase, thus significantly reducing the number of candidate points that need to be checked in the final merging phase. APS kyline is extremely efficient for hard cases of skyline processing, as in the cases of datasets with large skyline result sets, where it is meaningful to exploit multicore processing.

Top-k queries return to the user only the k best objects based on the individual user preferences and comprise an essential tool for rank-aware query processing. Assuming a stored data set of user preferences, reverse top-k queries have been introduced for retrieving the users that deem a given database object as one of their top-k results. Reverse top-k queries have already attracted significant interest in research, due to numerous real-life applications such as market analysis and product placement. Currently, the most efficient algorithm for computing the reverse top-k set is RTA. RTA has two main drawbacks when processing a reverse top-k query: (i) it needs to access all stored user preferences, and (ii) it cannot avoid executing a top-k query for each user preference that belongs to the result set. To address these limitations, in this paper, we identify useful properties for processing reverse top-k queries without accessing each user's individual preferences nor executing the top-k query. We propose an intuitive branch-and-bound algorithm for processing reverse top-k queries efficiently and discuss novel optimizations to boost its performance. Our experimental evaluation demonstrates the efficiency of the proposed algorithm that outperforms RTA by a large margin.

In applications such as market analysis, it is of great interest to product manufacturers to have their products ranked as highly as possible for a significant number of customers. However, customer preferences change over time, and product manufacturers are interested in monitoring the evolution of the popularity of their products, in order to discover those products that are consistently highly ranked. To take into account the temporal dimension, we define the continuous influential query and present algorithms for efficient processing and retrieval of continuous influential data objects. Furthermore, our algorithms support incremental retrieval of the next continuous influential data object in a natural way. To evaluate the performance of our algorithms, we conduct a detailed experimental study for various setups.

With the rapid growth of the Web, keyword-based searches become extremely ambiguous. To guide users to identify the results of their interest, in this paper, we consider an alternative way for presenting the results of a keyword search. In particular, we propose a framework for organizing the results into groups that contain results with similar content and refer to similar temporal characteristics. Moreover, we provide summaries of results as hints for query refinement. A summary of a result set is expressed as a set of popular keywords in the result set. Finally, we report evaluation results of the effectiveness of our approach.

Travel websites like TripAdvisor are nowadays important tools for travelers when deciding which hotels to stay in, and what restaurants and tourist attractions to visit. In this paper, we study opinion mining applied on data from travel review sites. We also describe how the results of sentiment analysis of textual reviews can be visualized using Google Maps, providing possibilities for users to easily detect good hotels and good areas to stay in. More advanced features also provides for faceted and filtered visualization. An evaluation of the techniques presented, shows high accuracy in opinion mining, and that the prototype can help detect hotel features and possible reasons for changes in opinion as well as show "good" and "bad" geographical areas based on hotel reviews.

Traditional document indexing techniques store documents using easily accessible representations, such as inverted indices, which can efficiently scale for large document sets. These structures offer scalable and efficient solutions in text document management tasks, though, they omit the cornerstone of the documents' purpose: meaning. They also neglect semantic relations that bind terms into coherent fragments of text that convey messages. When semantic representations are employed, the documents are mapped to the space of concepts and the similarity measures are adapted appropriately to better fit the retrieval tasks. However, these methods can be slow both at indexing and retrieval time. In this paper we propose SemaFor, an indexing algorithm for text documents, which uses semantic spanning forests constructed from lexical resources, like Wikipedia, and WordNet, and spectral graph theory in order to represent documents for further processing.

The MapReduce framework for parallel processing of massive data sets has attracted considerable attention recently, mainly due to its salient features that include scalability, simplicity, and fault-tolerance. However, despite its merits, MapReduce follows a brute-force approach, which often results in performing redundant work. This is particularly evident in the case of rank-aware queries, such as top-k, where a bounded set of k tuples comprise the result set. To process such queries in MapReduce, the input data needs to be accessed in its entirety, in order to produce the correct result set. To address this limitation of lack of early termination, in this paper, we investigate on different techniques that allow efficient processing of rank-aware queries, without accessing the input data exhaustively. We present various individual approaches that can be combined and demonstrate their advantages and shortcomings. Thus, we provide the first steps towards integrating efficient rank-aware processing in MapReduce.

In this paper, we study efficient processing of rank joins in highly distributed systems, where servers store fragments of relations in an autonomous manner. Existing rank-join algorithms exhibit poor performance in this setting due to excessive communication costs or high latency. We propose a novel distributed rank-join framework that employs data statistics, maintained as histograms, to determine the subset of each relational fragment that needs to be fetched to generate the top-k join results. At the heart of our framework lies a distributed score bound estimation algorithm that produces sufficient score bounds for each relation, that guarantee the correctness of the rank-join result set, when the histograms are accurate. Furthermore, we propose a generalization of our framework that supports approximate statistics, in the case that the exact statistical information is not available. An extensive experimental study validates the efficiency of our framework and demonstrates its advantages over existing methods.

With the popularization of GPS-enabled devices there is an increasing interest for location-based queries. In this context, one interesting problem is processing top-k spatial keyword queries. Given a set of objects with a textual description (e.g., menu of a restaurant), a query location (latitude and longitude), and a set of query keywords, a top-k spatial keyword query returns the k best objects ranked in terms of both distance to the query location and textual relevance to the query keywords. So far, the research on this problem has assumed Euclidean space. In order to process such queries efficiently, spatio-textual indexes combining R-trees and inverted files are employed. However, for most real applications, the distance between the objects and query location is constrained by a road network (shortest path) and cannot be computed efficiently using R-trees. In this paper, we address, for the first time, the challenging problem of processing top-k spatial keyword queries on road networks where the distance between the query location and the spatial object is the shortest path. We formalize the new query type, and present novel indexing structures and algorithms that are able to process such queries efficiently. Finally, we perform an experimental evaluation that shows the efficiency of our approach.

Recently, recommendation systems have received significant attention. However, most existing approaches focus on recommending items of potential interest to users, without taking into consideration how temporal information influences the recommendations. In this paper, we argue that time-aware recommendations need to be pushed in the foreground. We introduce an extensive model for time-aware recommendations from two perspectives. From a fresh-based perspective, we propose using a suite of aging schemes towards making recommendations mostly depend on fresh and novel user preferences. From a context-based perspective, we focus on providing different suggestions under different temporal specifications. The proposed strategies are experimentally evaluated using real movies ratings.

Recommendation systems have received significant attention, with most of the proposed methods focusing on recommendations for single users. Recently, there are also approaches aiming at either group or context-aware recommendations. In this paper, we address the problem of contextual recommendations for groups. We exploit a hierarchical context model to extend a typical recommendation model to a general context-aware one that tackles the information needs of a group. We base the computation of contextual group recommendations on a subset of preferences of the users that present the most similar behavior to the group, that is, the users with the most similar preferences to the preferences of the group members, for a specific context. This subset of preferences includes the ones with context equal to or more general than the given context.

Using keyword queries to find entities has emerged as one of the major search types on the Web. In this paper, we study the task of ad-hoc entity retrieval: keyword search in a collection of structured data. We start with a baseline retrieval system that constructs pseudo documents from RDF triples and introduce three extensions: preprocessing of URIs, using two-fielded retrieval models, and boosting popular domains. Using the query sets of the 2010 and 2011 Semantic Search Challenge, we show that our straightforward approach outperforms all previously reported results, some generated by far more complex systems.

In this chapter, a basic overview is given of P2P systems, architectures, and search strategies in P2P systems. More specific concepts that are outlined include the differences of structured and unstructured P2P systems, categories of P2P systems based on the centralization degree, basic search mechanisms for unstructured P2P systems, as well as details on P2P data management systems.

Recently there has been an increased interest in database management systems to incorporate and support more flexible query operators, such as top-k, that produce results of specified cardinality, thus avoiding huge and overwhelming result sets. Top-k queries retrieve the objects that best match the user requirements by employing user-specified scoring functions that result in an ordered set of objects containing the best k objects only [30, 75]. In this chapter, efficient processing of top-k queries in peer-to-peer systems is studied. To this end, the applicability of the skyline operator is investigated for efficiently answering top-k queries for a wide class of scoring functions, indicating user-specified preferences, in large P2P networks.

Entity search has emerged as an important research topic over the past years, but so far has only been addressed in a centralized setting. In this paper we present an attempt to solve the task of ad-hoc entity retrieval in a cooperative distributed environment. We propose a new collection ranking and selection method for entity search, called AENN. The key underlying idea is that a lean, name-based representation of entities can efficiently be stored at the central broker, which, therefore, does not have to rely on sampling. This representation can then be utilized for collection ranking and selection in a way that the number of collections selected and the number of results requested from each collection is dynamically adjusted on a per-query basis. Using a collection of structured datasets in RDF and a sample of real web search queries targeting entities, we demonstrate that our approach outperforms state-of-the-art distributed document retrieval methods in terms of both effectiveness and efficiency.

Increasingly many knowledge bases are published as Linked Data, driving the need for effective and efficient techniques for information access. Knowledge repositories are naturally organised around objects or entities and constitute a promising data source for entity-oriented search. There is a growing body of research on the subject, however, it is almost always (implicitly) assumed that a centralised index of all data is available. In this paper, we address the task of ranking distributed knowledge repositories--a vital component of federated search systems--and present two probabilistic methods based on generative language modeling techniques. We present a benchmarking testbed based on the test suites of the Semantic Search Challenge series to evaluate our approaches. In our experiments, we show that both our ranking approaches provide competitive performance and offer a viable alternative to centralised retrieval.

Similarity search in metric spaces has attracted much attention recently due to numerous applications, including multimedia retrieval and scientific data management. Several centralized indexing methods have been proposed to support efficient similarity search in metric spaces. In this chapter, a distributed framework termed SIMPEER [49] is presented for efficient similarity search in P2P systems that extends the basic concepts of an efficient approach that has been previously proposed for centralized systems. SIMPEER dynamically clusters peer data, in order to build distributed routing information at super-peer level. The usage of carefully designed distributed data summaries guarantees that all similar objects to the query are retrieved, without necessarily flooding the network during query processing. With SIMPEER, the targeted query types (range and nearest neighbor queries) can be efficiently evaluated, thus reducing communication cost, network latency, bandwidth consumption and computational overhead at each individual peer.

Retrieval effectiveness of temporal queries can be improved by taking into account the time dimension. Existing temporal ranking models follow one of two main approaches: 1) a mixture model linearly combining textual similarity and temporal similarity, and 2) a probabilistic model generating a query from the textual and temporal part of document independently. In this paper, we propose a novel time-aware ranking model based on learning-to-rank techniques. We employ two classes of features for learning a ranking model, entity-based and temporal features, which are derived from annotation data. Entity-based features are aimed at capturing the semantic similarity between a query and a document, whereas temporal features measure the temporal similarity. Through extensive experiments we show that our ranking model significantly improves the retrieval effectiveness over existing time-aware ranking models.

The Web of Data describes objects, entities, or "things" in terms of their attributes and their relationships, using RDF statements. There is a need to make this wealth of knowledge easily accessible by means of keyword search. Despite recent research efforts in this direction, there is a lack of understanding of how structured semantic data is best represented for text-based entity retrieval. The task we are addressing in this paper is ad-hoc entity search: the retrieval of RDF resources that represent an entity described in the keyword query. We build upon and formalise existing entity modeling approaches within a generative language modeling framework, and compare them experimentally using a standard test collection, provided by the Semantic Search Challenge evaluation series. We show that these models outperform the current state-of-the-art in terms of retrieval effectiveness, however, this is done at the cost of abandoning a large part of the semantics behind the data. We propose a novel entity model capable of preserving the semantics associated with entities, without sacrificing retrieval effectiveness.

Skyline queries help users make intelligent decisions over complex data, when different and often conflicting criteria are considered. Such queries return a set of data points that are not dominated by any other point on all dimensions. Skyline queries have been studied in centralized systems and more recently in distributed environments, such as web information systems and peer-to-peer (P2P) networks. Skyline query processing in P2P networks poses inherent challenges and demands non-traditional techniques due to the distribution of content and the lack of global knowledge. Distributed skyline processing should minimize transfer of globally dominated data points. Moreover, peers that do not store any global skyline points, ideally should not be contacted at all. Detecting domination between points that are stored by different peers is challenging and requires usage of summary information that describes the data stored locally and across the network. In this section, we describe in details a distributed framework for subspace skyline processing, called SKYPEER+ [130]. SKYPEER+ reduces both computational time and volume of transmitted data due to (i) efficient routing of skyline queries over the super-peer network, and (ii) an effective thresholding and indexing scheme for discarding dominated points.

Understanding the structure of complex networks and uncovering the properties of their constituents has been for many decades at the center of study of several fundamental sciences, such as discrete mathematics and graph theory. Especially during the previous decade, we have witnessed an explosion in complex network data, with two cornerstone paradigms being the biological networks and the social networks. The large scale, but also the complexity, of these types of networks constitutes the need for efficient graph mining algorithms. In both examples, one of the most important tasks is to identify closely connected network components comprising nodes that share similar properties. In the case of biological networks, this could mean the identification of proteins that bind together to carry their biological function, while in the social networks, this can be seen as the identification of communities. Motivated by this analogy, we apply the Power Graph Analysis methodology, for the first time to the best of our knowledge, to the field of community mining. The model was introduced in bioinformatics research and in this work is applied to the problem of community detection in complex networks. The advances in the field of community mining allow us to experiment with widely accepted benchmark data sets, and our results show that the suggested methodology performs favorably against state of the art methods for the same task, especially in networks with large numbers of nodes.

In this paper, we study the generation of efficient execution plans for skyline query processing in large-scale distributed environments. In such a setting, each server stores autonomously a fraction of the data, thus all servers need to process the skyline query. An execution plan defines the order in which the individual skyline queries are processed on different servers, and influences the performance of query processing. Querying servers consecutively reduces the amount of transferred data and the number of queried servers, since skyline points obtained by one server prune points in the subsequent servers, but also increases the latency of the system. To address this trade-off, we introduce a novel framework, called SkyPlan, for processing distributed skyline queries that generates execution plans aiming at optimizing the performance of query processing. Thus, we quantify the gain of querying consecutively different servers. Then, execution plans are generated that maximize the overall gain, while also taking into account additional objectives, such as bounding the maximum number of hops required for the query or balancing the load on different servers fairly. Finally, we present an algorithm for distributed processing based on the generated plan that continuously refines the execution plan during in-network processing. Our framework consistently outperforms the state-of-the-art algorithm.

Semantic caching augments cached data with a semantic description of the data. These semantic descriptions can be used to improve execution time for similar queries by retrieving some data from cache and issuing a remainder query for the rest. This is an improvement over traditional page caching, since caches are no longer limited to only base tables but are extended to contain intermediate results. In large-scale distributed database systems, using a central server with complete knowledge of the system will be a serious bottleneck and single point of failure. In this paper, we propose a distributed semantic caching method where sites make autonomous caching decisions based on locally available information, thereby reducing the need for centralized control. We implement the method in the DASCOSA-DB distributed database system prototype and use this implementation to do experiments that show the applicability and efficiency of our approach. Our evaluation shows that execution times for queries with similar subqueries are significantly reduced and that overhead caused by cache management is marginal.

Computational science applications performing distributed computations using grid networks are now emerging. These applications have new and demanding requirements for efficient query processing. To meet these requirements, we have developed the DASCOSA-DB distributed database system. In this chapter, a detailed overview of the architecture and implementation of DASCOSA-DB is given, as well as a description of novel features developed to better support typical data-intensive applications running on a grid system: fault-tolerant query processing, dynamic refragmentation, allocation and replication of data fragments, and distributed semantic caching.

Text categorisation relies heavily on feature selection. Both the possible reduction in dimensionality as well as improvements in classification performance are highly desirable. To the end of feature selection for text, a range of different methods have been developed, each having unique properties and selecting different features. However, it remains unclear which of them can be combined and what benefits this brings with it. In this paper we present correlation methods for the analysis of feature rankings and evaluate the combination of features according to these metrics. We further show results of an extensive study of feature selection approaches using a wide range of combination methods. We performed experiments on 19 test collections and report our findings.

Given a spatial location and a set of keywords, a top-k spatial keyword query returns the k best spatio-textual objects ranked according to their proximity to the query location and relevance to the query keywords. There are many applications handling huge amounts of geotagged data, such as Twitter and Flickr, that can benefit from this query. Unfortunately, the state-of-the-art approaches require non-negligible processing cost that incurs in long response time. In this paper, we propose a novel index to improve the performance of top-k spatial keyword queries named Spatial Inverted Index (S2I). Our index maps each distinct term to a set of objects containing the term. The objects are stored differently according to the document frequency of the term and can be retrieved efficiently in decreasing order of keyword relevance and spatial proximity. Moreover, we present algorithms that exploit S2I to process top-k spatial keyword queries efficiently. Finally, we show through extensive experiments that our approach outperforms the state-of-the-art approaches in terms of update and query cost.

Feature selection plays a vital role in text categorisation. A range of different methods have been developed, each having unique properties and selecting different features. We show some results of an extensive study of feature selection approaches using a wide range of combination methods. We performed experiments on 18 test collections and report a subset of the results.

Bibliographic databases are a prosperous field for data mining research and social network analysis. The representation and visualization of bibliographic databases as graphs and the application of data mining techniques can help us uncover interesting knowledge regarding how the publication records of authors evolve over time. In this paper we propose a novel methodology to model bibliographical databases as Power Graphs, and mine them in an unsupervised manner, in order to learn basic author types and their properties through clustering. The methodology takes into account the evolution of the co-authorship information, the volume of published papers over time, as well as the impact factors of the venues hosting the respective publications. As a proof of concept of the applicability and scalability of our approach, we present experimental results in the DBLP data.

The Affinity Propagation (AP) clustering algorithm proposed by Frey and Dueck (2007) provides an understandable, nearly optimal summary of a data set. However, it suffers two major shortcomings: i) the number of clusters is vague with the user-defined parameter called self-confidence, and ii) the quadratic computational complexity. When aiming at a given number of clusters due to prior knowledge, AP has to be launched many times until an appropriate setting of self-confidence is found. The re-launched AP increases the computational cost by one order of magnitude. In this paper, we propose an algorithm, called K-AP, to exploit the immediate results of K clusters by introducing a constraint in the process of message passing. Through theoretical analysis and experimental validation, K-AP was shown to be able to directly generate K clusters as user defined, with a negligible increase of computational cost compared to AP. In the meanwhile, KAP preserves the clustering quality as AP in terms of the distortion. K-AP is more effective than k-medoids w.r.t. the distortion minimization and higher clustering purity.

Recently, the problem of efficiently supporting advanced query operators, such as nearest neighbor or range queries, over multidimensional data in widely distributed environments has attracted much attention. In unstructured peer-to-peer (P2P) networks, peers store data in an autonomous manner, thus multidimensional routing indices (MRI) are required, in order to route user queries efficiently to only those peers that may contribute to the query result set. Focusing on a hybrid unstructured P2P network, in this paper, we analyze the parameters for building MRI of high selectivity. In the case where similar data are located at different parts of the network, MRI exhibit extremely poor performance, which renders them ineffective. We present algorithms that boost the query routing performance by detecting similar peers and reassigning these peers to other parts of the hybrid network in a distributed and scalable way. The resulting MRI are able to eagerly discard routing paths during query processing. We demonstrate the advantages of our approach experimentally and show that our framework enhances a state-of-the-art approach for similarity search in terms of reduced network traffic and number of contacted peers.

Recent research works on unsupervised word sense disambiguation report an increase in performance, which reduces their handicap from the respective supervised approaches for the same task. Among the latest state of the art methods, those that use semantic graphs reported the best results. Such methods create a graph comprising the words to be disambiguated and their corresponding candidate senses. The graph is expanded by adding semantic edges and nodes from a thesaurus. The selection of the most appropriate sense per word occurrence is then made through the use of graph processing algorithms that offer a degree of importance among the graph vertices. In this paper we experimentally investigate the performance of such methods. We additionally evaluate a new method, which is based on a recently introduced algorithm for computing similarity between graph vertices, P-Rank. We evaluate the performance of all alternatives in two benchmark data sets, Senseval 2 and 3, using WordNet. The current study shows the differences in the performance of each method, when applied on the same semantic graph representation, and analyzes the pros and cons of each method for each part of speech separately. Furthermore, it analyzes the levels of inter-agreement in the sense selection level, giving further insight on how these methods could be employed in an unsupervised ensemble for word sense disambiguation.

Recent work on analyzing query logs shows that a significant fraction of queries are temporal, i.e., relevancy is dependent on time, and temporal queries play an important role in many domains, e.g., digital libraries and document archives. Temporal queries can be divided into two types: 1) those with temporal criteria explicitly provided by users, and 2) those with no temporal criteria provided. In this paper, we deal with the latter type of queries, i.e., queries that comprise only keywords, and their relevant documents are associated to particular time periods not given by the queries. We propose a number of methods to determine the time of queries using temporal language models. After that, we show how to increase the retrieval effectiveness by using the determined time of queries to re-rank the search results. Through extensive experiments we show that our proposed approaches improve retrieval effectiveness.

Traditional routing indices in peer-to-peer (P2P) networks are mainly designed for document retrieval applications and maintain aggregated one-dimensional values representing the number of documents that can be obtained in a certain direction in the network. In this paper, we introduce the concept of multidimensional routing indices (MRIs), which are suitable for handling multidimensional data represented by minimum bounding regions (MBRs). Depending on data distribution on peers, the aggregation of the MBRs may lead to MRIs that exhibit extremely poor performance, which renders them ineffective. Thus, focusing on a hybrid unstructured P2P network, we analyze the parameters for building MRIs of high selectivity. We present techniques that boost the query routing performance by detecting similar peers and grouping and reassigning these peers to other parts of the hybrid network in a distributed and scalable way. We demonstrate the advantages of our approach using large-scale simulations.

In this paper we introduce a novel approach for the thematic organization of bibliographic records that builds upon a semantic relatedness measure we have implemented for this task. In particular, we introduce the Omiotis measure, which captures the semantic relatedness between text segments and enables the thematic organization of the bibliographic data stored in online databases. Experimental evaluation demonstrates that Omiotis can significantly improve the performance of several data mining tasks, such as publications' classification and clustering, compared to existing approaches; even when considering a limited amount of information, i.e., the paper titles.

Semantic Overlay Networks (SONs) have been recently proposed as a way to organize content in peer-to-peer (P2P) networks. The main objective is to discover peers with similar content and then form thematically focused peer groups. Efficient content retrieval can be performed by having queries selectively forwarded only to relevant groups of peers to the query. As a result, less peers need to be contacted, in order to answer a query. In this context, the challenge is to generate SONs in a decentralized and distributed manner, as the centralized assembly of global information is not feasible. Different approaches for exploiting the generated SONs for content retrieval have been proposed in the literature, which are examined in this chapter, with a particular focus on SON interconnections for efficient search. Several applications, such as P2P document and image retrieval, can be deployed over generated SONs, motivating the need for distributed and truly scalable SON creation. Therefore, recently several research papers focus on SONs as stated in our comprehensive overview of related work in the field of semantic overlay networks. A classification of existing algorithms according to a set of qualitative criteria is also provided. In spite of the rich existing work in the field of SONs, several challenges have not been efficiently addressed yet, therefore, future promising research directions are pointed out and discussed at the end of this chapter.

Requirements from new types of applications call for new database system solutions. Computational science applications performing distributed computations on Grid networks with requirements for efficient storage and query solutions are now emerging. For this purpose we have developed DASCOSA-DB, a P2P-based distributed database system, which in addition to providing location-transparent storage and querying, also includes novel features like efficient partial restartof queries and redistribution of query operators in the context of failure, dynamic refragmentation and allocation, and distributed semantic caching. In this demo, the novel features will be demonstrated, combined with a more general description of the architecture and demonstration of the distributed query processing capabilities.

In this paper we present a new approach for measuring the relatedness between text segments, based on implicit semantic links between their words, as offered by a word thesaurus, namely WordNet. The approach does not require any type of training, since it exploits only WordNet to devise the implicit semantic links between text words. The paper presents a prototype on-line demo of the measure, that can provide word-to-word relatedness values, even for words of different part of speech. In addition the demo allows for the computation of relatedness between text segments.