Journal of Information Science

Finding k-nearest neighbours (k-NN) is one of the most important primitives of many applications such as search engines and recommendation systems. However, its computational cost is extremely high when searching for k-NN points in a huge collection of high-dimensional points. Locality-sensitive hashing (LSH) has been introduced for an efficient k-NN approximation, but none of the existing LSH approaches clearly outperforms others. We propose a novel LSH approach, Signature Selection LSH (S2LSH), which finds approximate k-NN points very efficiently in various datasets. It first constructs a large pool of highly diversified signature regions with various sizes. Given a query point, it dynamically generates a query-specific signature region by merging highly effective signature regions selected from the signature pool. We also suggest S2LSH-M, a variant of S2LSH, which processes multiple queries more efficiently by using query-specific features and optimization techniques. Extensive experiments show the performance superiority of our approaches in diverse settings.

Financial news plays a significant role with regard to predicting the behaviour of financial markets. However, the exponential growth of financial news on the Web has led to a need for new technologies that automatically collect and categorise large volumes of information in a fast and easy manner. Sentiment analysis, or opinion mining, is the field of study that analyses people’s opinions, moods and evaluations using written text on Web platforms. In recent research, a substantial effort has been made to develop sophisticated methods with which to classify sentiments in the financial domain. However, there is a lack of approaches that analyse the positive or negative orientation of each aspect contained in a document. In this respect, we propose a new sentiment analysis method for feature and news polarity classification. The method presented is based on an ontology-driven approach that makes it possible to semantically describe relations between concepts in the financial news domain. The polarity of the features in each document is also calculated by taking into account the words from around the linguistic expression of the feature. These words are obtained by using the ‘N_GRAM After’, ‘N_GRAM Before’, ‘N_GRAM Around’ and ‘All_Phrase’ methods. The effectiveness of our method has been proved by carrying out a set of experiments on a corpus of 1000 financial news items. Our proposal obtained encouraging results with an accuracy of 66.7% and an F-measure of 64.9% for feature polarity classification and an accuracy of 89.8% and an F-measure of 89.7% for news polarity classification. The experimental results additionally show that the N_GRAM Around method provides the best average results.

Clustering is a very useful technique to categorise Web users with common browsing activities, access patterns and navigational behaviour. Web user clustering is used to build Web visitor profiles that make the core of a personalised information recommender system. These systems are used to comprehend Web users surfing activities by offering tailored content to Web users with similar interests. The principle objective of Web user sessions clustering is to maximise the intra-group while minimising the inter-group similarity. Efficient clustering of Web users’ sessions not only depend on the clustering algorithm’s nature but also depend on how well user concerns are captured and accommodated by the dissimilarity measure that are used. Determining the right dissimilarity measure to capture the access behaviour of the Web user is very significant for substantial clustering. In this paper, an intuitive dissimilarity measure is presented to estimate a Web user’s concern from augmented Web user sessions. The proposed usage dissimilarity measure between two Web user sessions is based on the accessing page relevance, the syntactic structure of page URL and hierarchical structure of the website. This proposed intuitive dissimilarity measure was used with K-Medoids Clustering algorithm for experimentation and results were compared with other independent dissimilarity measures. The worth of the generated clusters were evaluated by two unsupervised cluster validity indexes. The experimental results show that intuitive augmented session dissimilarity measure is more realistic and superior as compared to the other independent dissimilarity measures regarding cluster validity indexes.

The vehicle to represent Knowledge Organisation Systems (KOSs) in the environment of the Semantic Web and linked data is the Simple Knowledge Organisation System (SKOS). SKOS provides a way to assign a Uniform Resource Identifier (URI) to each concept, and this URI functions as a surrogate for the concept. This fact makes of main concern the need to clarify the URIs’ ontological meaning. The aim of this study is to investigate the relationship between the ontological substance of KOS concepts and concepts revealed through the grammatical and syntactic formalisms of natural language. For this purpose, we examined the dividableness of concepts in specific KOSs (i.e. a thesaurus, a subject headings system and a classification scheme) by applying Natural Language Processing (NLP) techniques (i.e. morphosyntactic analysis) to the lexical representations (i.e. RDF literals) of SKOS concepts. The results of the comparative analysis reveal that, despite the use of multi-word units, thesauri tend to represent concepts in a way that can hardly be further divided conceptually, while subject headings and classification schemes – to a certain extent – comprise terms that can be decomposed into more conceptual constituents. Consequently, SKOS concepts deriving from thesauri are more likely to represent atomic conceptual units and thus be more appropriate tools for inference and reasoning. Since identifiers represent the meaning of a concept, complex concepts are neither the most appropriate nor the most efficient way of modelling a KOS for the Semantic Web.

It is important to obtain public opinion about a news article. Microblogs such as Twitter are popular and an important medium for people to share ideas. An important portion of tweets are related to news or events. Our aim is to find tweets about newspaper reports and measure the popularity of these reports on Twitter. However, it is a challenging task to match informal and very short tweets with formal news reports. In this study, we formulate this problem as a supervised classification task. We propose to form a training set using tweets containing a link to the news and the content of the same news article. We preprocess tweets by removing unnecessary words and symbols and apply stemming by means of morphological analysers. We apply binary classifiers and anomaly detection to this task. We also propose a textual similarity-based approach. We observed that preprocessing of tweets increases accuracy. The textual similarity method obtains results with the highest recognition rate. Success increases in some cases when report text is used with tweets containing a link to the news report within the training set of classification studies. We propose that this study, which is made directly in consideration of tweet texts that measure the trends of national newspaper reports on social media, has a higher significance when compared to Twitter analyses made by using a hashtag. Given the limited number of scientific studies on Turkish tweets, this study makes a contribution to the literature.

Integration of library data into the Semantic Web environment is a key issue for libraries and is approached on the basis of interoperability between conceptual models. Several data models exist for the representation and publication of library data in the Semantic Web and therefore inter-domain and intra-domain interoperability issues emerge as a growing number of web data are generated. Achieving interoperability for different representations of the same or related entities between the library and other cultural heritage institutions shall enhance rich bibliographic data reusability and support the development of new data-driven information services. This paper aims to investigate common ground and convergences between four conceptual models, namely Functional Requirements for Bibliographic Records (FRBR), FRBR Object-Oriented (FRBRoo), Bibliographic Framework (BIBFRAME) and Europeana Data Model (EDM), enabling semantically-richer interoperability by studying the representation of monographs, as well as of content relationships (derivative and equivalent bibliographic relationships) and of whole-part relationships between them.

Professionally, people often conduct their work in settings containing a range of different collaborative situations and work practices in which people handle information and work activities. Still, work tasks are usually considered and perceived as individual activities although the technology and the characteristics of the tasks require collaborative and cooperative handling processes. This viewpoint still produces technologies that, in general, assume individual information management and decision-making. Based on previous research on information culture (IC) and collaborative information seeking (CIS), this paper proposes an integrated framework where both environmental (cultural) as well as collaborative aspects of organisational information behaviour are present. This kind of framework would be useful in studies looking into how information is retrieved, how information is organised and managed, and how information is used as a resource in collaborative settings. It gives a more holistic perspective to information use and practices in organisations where culture, collaboration and awareness are especially brought to common attention for effective information management in organisations.

Collaborative filtering is a popular strategy in recommender systems area. This approach gathers users’ ratings and then predicts what users will rate based on their similarity to other users. However, most of the collaborative filtering methods have faced problems such as sparseness and scalability. This paper presents a non-negative matrix factorisation method to alleviate these problems via decomposing rating matrix into user matrix and item matrix. This method tries to find two non-negative user matrix and item matrix whose product can well estimate the rating matrix. This approach proposes updated rules to learn the latent factors for factorising the rating matrix. The proposed method can estimate all the unknown ratings and its computational complexity is very low. Empirical studies on benchmark datasets show that the proposed method is more tolerant of the sparseness and scalability problems.