Search results

Traditional library book recommendation methods are mainly based on association rules and user profiles. They may help to learn about students' interest in different types of books, e.g., students majoring in science and engineering tend to pay more attention to computer books. Nevertheless, most of them still need to identify users' interests accurately. To solve the problem, the authors propose a novel embedding-driven model called InFo, which refers to users' intrinsic interests and academic preferences to provide personalized library book recommendations.

The authors analyze the characteristics and challenges in real library book recommendations and then propose a method considering feature interactions. Specifically, the authors leverage the attention unit to extract students' preferences for different categories of books from their borrowing history, after which we feed the unit into the Factorization Machine with other context-aware features to learn students' hybrid interests. The authors employ a convolution neural network to extract high-order correlations among feature maps which are obtained by the outer product between feature embeddings.

The authors evaluate the model by conducting experiments on a real-world dataset in one university. The results show that the model outperforms other state-of-the-art methods in terms of two metrics called Recall and NDCG.

It requires a specific data size to prevent overfitting during model training, and the proposed method may face the user/item cold-start challenge.

The embedding-driven book recommendation model could be applied in real libraries to provide valuable recommendations based on readers' preferences.

The proposed method is a practical embedding-driven model that accurately captures diverse user preferences.

This paper aims to highlight the impact of big data on library services. This study highlights the required skills of librarians and the application of big data analytics.

An analysis of the literature was also used to identify the various applications implemented in library services across the globe.

This study’s findings reveal that the role of big data remained limited because of a lack of knowledge and skills. Big data’s significant challenges include inadequate technical support, untrained librarians and financial constraints to meet these requirements. This paper highlighted the challenges and remedial measures that can be taken while adopting this technology in library services.

This paper is significant for librarians, practitioners and stakeholders of the various organization who desire to implement this technology in their respective libraries.

In order to estimate the value of semi-automated subject indexing in operative library catalogues, the study aimed to investigate five different automated implementations of an open source software package on a large set of Swedish union catalogue metadata records, with Dewey Decimal Classification (DDC) as the target classification system. It also aimed to contribute to the body of research on aboutness and related challenges in automated subject indexing and evaluation.

On a sample of over 230,000 records with close to 12,000 distinct DDC classes, an open source tool Annif, developed by the National Library of Finland, was applied in the following implementations: lexical algorithm, support vector classifier, fastText, Omikuji Bonsai and an ensemble approach combing the former four. A qualitative study involving two senior catalogue librarians and three students of library and information studies was also conducted to investigate the value and inter-rater agreement of automatically assigned classes, on a sample of 60 records.

The best results were achieved using the ensemble approach that achieved 66.82% accuracy on the three-digit DDC classification task. The qualitative study confirmed earlier studies reporting low inter-rater agreement but also pointed to the potential value of automatically assigned classes as additional access points in information retrieval.

The paper presents an extensive study of automated classification in an operative library catalogue, accompanied by a qualitative study of automated classes. It demonstrates the value of applying semi-automated indexing in operative information retrieval systems.

With the technological innovation dominating higher education, the university libraries, as physical spaces, continue to play a crucial role in connecting students with knowledge. The emergence of the “Learning Commons” serves as a catalyst in the design of library spaces, renewing libraries’ roles and missions and making them popular to Millennials for new reasons. This study aims to record Greek librarians' views on the current situation in Greek academic libraries regarding physical space design, services provided and the existence of the “Learning Commons” model characteristics.

This study was conducted through an online survey structured questionnaire (closed-ended, five-point Likert scale, multiple-choice and statements questions). This study population comprised librarians working in 37 academic institutions and colleges. The collected data were subjected to descriptive statistical analysis. The research questions were answered using variables creation and the tests, t-test, ANOVA and Kruskal–Wallis. The groups of questions were tested for their reliability using the Cronbach's alpha coefficient.

In total, 186 librarians responded to this study. The responses revealed that participants were willing and ready to accept and support a different approach to academic library physical spaces use, according to the shared learning spaces model. However, this requires changes in the organization's vision, further growth and evolution. Although recently most Greek academic libraries have made significant progress in developing their services to function as information and digital hubs, they do not function as learning collaborative hubs, since the “Learning Commons” model is not reflected in their buildings.

The creation of new academic libraries according to the “common” model is a rapidly evolving issue that affects Greek libraries. This paper highlights the characteristics of libraries that should be adopted in the modern era, the new roles of academic librarians and the importance of an appropriate design of the physical space to achieve optimal learning outcomes. At the same time, this paper is one of the few that illustrates librarians', and not users', perceptions of these changes. This paper is a good research example, and the methodology for measuring this type of context could be used by other future research approaches in other countries.

This study aims to adjust Thesis-type properties on Schema.org using metadata models and standards (MS) (Bibframe, electronic thesis and dissertations [ETD]-MS, Common European Research Information Format [CERIF] and Dublin Core [DC]) to enrich the Thesis-type properties for better description and processing on the Web.

This study is applied, descriptive analysis in nature and is based on content analysis in terms of method. The research population consisted of elements and attributes of the metadata model and standards (Bibframe, ETD-MS, CERIF and DC) and Thesis-type properties in the Schema.org. The data collection tool was a researcher-made checklist, and the data collection method was structured observation.

The results show that the 65 Thesis-type properties and the two levels of Thing and CreativeWork as its parents on Schema.org that corresponds to the elements and attributes of related models and standards. In addition, 12 properties are special to the Thesis type for better comprehensive description and processing, and 27 properties are added to the CreativeWork type.

Enrichment and expansion of Thesis-type properties on Schema.org is one of the practical applications of the present study, which have enabled more comprehensive description and processing and increased access points and visibility for ETDs in the environment Web and digital libraries.

This study has offered some new Thesis type properties and CreativeWork levels on Schema.org. To the best of the authors’ knowledge, this is the first time this issue is investigated.

The article investigates the institutional setup of e-lending in public libraries in Denmark, Norway and Sweden. Our point of departure is that e-lending has necessitated new library collaborations between local, regional and national levels, and therefore, institutional e-lending setups have emerged. The study seeks to provide better understanding of how the institutional setups are structured, how governance logics have shaped them and what tensions and dynamics become visible in the key actors’ problematisations of these setups.

The study is situated in the neo-institutional tradition and applies the institutional logics perspective. The research questions are answered by taking a qualitative approach, grounded in an extensive interview study with representatives of libraries, publishers and policy actors in three Scandinavian countries. To provide in-depth insight into e-lending setups, the scope of empirical material is then limited to accounts the central library and policy actors involved in establishing e-lending.

The analysis shows that the e-lending setups are both similar (especially when it comes to financing), and different across Scandinavia, especially when it comes to centralisation and involvement of librarians in this task. The differences are attributed to the influence of different governance logics (question of administrative autonomy, collaboration in the field and existing legal and political frames), and to what extent the digital and market logics are incorporated or rejected in the field.

The study provides new insights into the question of how Scandinavian public libraries face the consequences of the digitalisation of book distribution and consumption by investigating how they organise their e-lending services. This has not been explored before, notably in a comparative perspective.

The digital contents (d-contents) are vulnerable to various threats either natural or manmade. Digital preservation is the plethora of a wide array of strategies necessary for the long-term preservation of digital objects. This study was carried out to assess the digital preservation practices for information resources in university libraries of Pakistan.

A quantitative survey based on a structured questionnaire was carried out to conduct the study. The questionnaire containing two sets of strategies (general and technical) was distributed amongst the whole population and received 90% response rate.

Overall, progressive implementation of general digital preservation practices was noted in these libraries like checking the digital collections for viruses, keeping the digital media in fire/water/theft proof locations, restricting unauthorized access, maintaining ideal humidity and temperature, and checking the digital media for functionality. Amongst the technical practices, only replication was in practice at a progressive rate, followed by metadata recording and media refreshing that was sometimes practiced in these libraries. The other technical practices were rarely or never practiced in these libraries. Significant variances in general and technical digital preservation practices were noted based on their physical locations (regional distribution).

The study contributes a comprehensive set of digital preservation practices divided into general and technical types to conduct similar studies in other parts of the world.

The findings stress the need for national and institutional policies, funding streams and skill enhancement of library staff.

The study fills the literature gap and contributes a comprehensive set of digital preservation practices divided into general and technical types to conduct similar studies in other parts of the world.

The peer-review history for this article is available at: https://publons.com/publon/10.1108/OIR-02-2023-0074

The purpose of this article is to contribute to the digital development and utilization of China’s intangible cultural heritage resources, research on the theft of intangible cultural heritage resources and knowledge integration based on linked data is proposed to promote the standardized description of intangible cultural heritage knowledge and realize the digital dissemination and development of intangible cultural heritage.

In this study, firstly, the knowledge organization theory and semantic Web technology are used to describe the intangible cultural heritage digital resource objects in metadata specifications. Secondly, the ontology theory and technical methods are used to build a conceptual model of the intangible cultural resources field and determine the concept sets and hierarchical relationships in this field. Finally, the semantic Web technology is used to establish semantic associations between intangible cultural heritage resource knowledge.

The study findings indicate that the knowledge organization of intangible cultural heritage resources constructed in this study provides a solution for the digital development of intangible cultural heritage in China. It also provides semantic retrieval with better knowledge granularity and helps to visualize the knowledge content of intangible cultural heritage.

This study summarizes and provides significant theoretical and practical value for the digital development of intangible cultural heritage and the resource description and knowledge fusion of intangible cultural heritage can help to discover the semantic relationship of intangible cultural heritage in multiple dimensions and levels.

This study aims to determine the most similar set of recommendation books to the user selections in LibraryThing.

For this purpose, 30,000 tags related to History on the LibraryThing have been selected. Their tags and the tags of the related recommended books were extracted from three different recommendations sections on LibraryThing. Then, four similarity criteria of Jaccard coefficient, Cosine similarity, Dice coefficient and Pearson correlation coefficient were used to calculate the similarity between the tags. To determine the most similar recommended section, the best similarity criterion had to be determined first. So, a researcher-made questionnaire was provided to History experts.

The results showed that the Jaccard coefficient, with a frequency of 32.81, is the best similarity criterion from the point of view of History experts. Besides, the degree of similarity in LibraryThing recommendations section according to this criterion is equal to 0.256, in the section of books with similar library subjects and classifications is 0.163 and in the Member recommendations section is 0.152. Based on the findings of this study, the LibraryThing recommendations section has succeeded in introducing the most similar books to the selected book compared to the other two sections.

To the best of the authors’ knowledge, itis for the first time, three sections of LibraryThing recommendations are compared by four different similarity criteria to show which sections would be more beneficial for the user browsing. The results showed that machine recommendations work better than humans.

This research aims to analyse the current state of research on the application of Artificial Intelligence (AI) in libraries by examining document type, publication year, keywords, country and research methods. The overarching aim is to enrich the existing knowledge of AI-powered libraries by identifying the prevailing research gaps, providing direction for future research and deepening the understanding needed for effective policy development.

This study used advanced tools such as bibliometric and network analysis, taking the existing literature from the SCOPUS database extending to the year 2022. This study analysed the application of AI in libraries by identifying and selecting relevant keywords, extracting the data from the database, processing the data using advanced bibliometric visualisation tools and presenting and discussing the results. For this comprehensive research, the search strategy was approved by a panel of computer scientists and librarians.

The majority of research concerning the application of AI in libraries has been conducted in the last three years, likely driven by the fourth industrial revolution. Results show that highly cited articles were published by Emerald Group Holdings Ltd. However, the application of AI in libraries is a developing field, and the study highlights the need for more research in areas such as Digital Humanities, Machine Learning, Robotics, Data Mining and Big Data in Academic Libraries.

This study has excluded papers written in languages other than English that address domains beyond libraries, such as medicine, health, education, science and technology.

This article offers insight for managers and policymakers looking to implement AI in libraries. By identifying clusters and themes, the article would empower managers to plan ahead, mitigate potential drawbacks and seize opportunities for sustainable growth.

Previous studies on the application of AI in libraries have taken a broad approach, but this study narrows its focus to research published explicitly in Library and Information Science (LIS) journals. This makes it unique compared to previous research in the field.