Improve Information Retrieval Research Articles

Converting and evolving a subject heading list into a thesaurus

PurposeThe objective of this paper is to describe the evolution of the available subject heading list, i.e. the CC Soggettario (Carabinieri Corps Soggettario), towards a thesaurus, that is CCThes (Carabinieri Corps Thesaurus), to support subject indexing and retrieval of the documentary heritage held by the Historical Office of the General Command of the Carabinieri Corps. This work follows the need to implement a controlled vocabulary compliant with the state-of-the-art standards.Design/methodology/approachThe methodology implements the practice of reengineering available vocabularies, following standardised guidelines for thesaurus development. The conversion process includes the balance maintenance of what has been achieved in the CC Soggettario and the enrichment of the semantic structure in the thesaurus by using both deductive and inductive methods.FindingsThe main result of this study is a thesaurus compliant with ISO 29964-1:2011 recommendations, which improves information retrieval performances and interoperability with other vocabularies and applications. It generally has a mono-hierarchical structure with the possibility of admitting, as an exception, the poly-hierarchy for a few concepts. An introductive user guide has been created as a complementary tool to the CCThes.Originality/valueThis is an applied study which deals with Knowledge Organisation System (KOS) reengineering and outlines this process using a pragmatic approach. The paper strength lies in providing the description of performed activities and conveying a set of resources to approach KOS reengineering practice. The study is also relevant for the preservation and diffusion of a part of the social memory and identity of Italy.

Converting and evolving a subject heading list into a thesaurus

PurposeThe objective of this paper is to describe the evolution of the available subject heading list, i.e. the CC Soggettario (Carabinieri Corps Soggettario), towards a thesaurus, that is CCThes (Carabinieri Corps Thesaurus), to support subject indexing and retrieval of the documentary heritage held by the Historical Office of the General Command of the Carabinieri Corps. This work follows the need to implement a controlled vocabulary compliant with the state-of-the-art standards.Design/methodology/approachThe methodology implements the practice of reengineering available vocabularies, following standardised guidelines for thesaurus development. The conversion process includes the balance maintenance of what has been achieved in the CC Soggettario and the enrichment of the semantic structure in the thesaurus by using both deductive and inductive methods.FindingsThe main result of this study is a thesaurus compliant with ISO 29964-1:2011 recommendations, which improves information retrieval performances and interoperability with other vocabularies and applications. It generally has a mono-hierarchical structure with the possibility of admitting, as an exception, the poly-hierarchy for a few concepts. An introductive user guide has been created as a complementary tool to the CCThes.Originality/valueThis is an applied study which deals with Knowledge Organisation System (KOS) reengineering and outlines this process using a pragmatic approach. The paper strength lies in providing the description of performed activities and conveying a set of resources to approach KOS reengineering practice. The study is also relevant for the preservation and diffusion of a part of the social memory and identity of Italy.

From traditional to tech-savvy: the evolution of Nigerian libraries in the machine learning era

Purpose This study explores the implementation of personalised information access, driven by machine learning, in Nigerian public libraries. The purpose of this paper is to address existing challenges, enhance the user experience and bridge the digital divide by leveraging advanced technologies. Design/methodology/approach This study assesses the current state of Nigerian public libraries, emphasising challenges such as underfunding and lack of technology adoption. It proposes the integration of machine learning to provide personalised recommendations, predictive analytics for collection development and improved information retrieval processes. Findings The findings underscore the transformative potential of machine learning in Nigerian public libraries, offering tailored services, optimising resource allocation and fostering inclusivity. Challenges, including financial constraints and ethical considerations, are acknowledged. Originality/value This study contributes to the literature by outlining strategies for responsible implementation and emphasising transparency, user consent and diversity. The research highlights future directions, anticipating advancements in recommendation systems and collaborative efforts for impactful solutions.

From Dewey to Deep Learning: Exploring the Intellectual Renaissance of Libraries through Artificial Intelligence

Libraries are embracing the potential of Artificial Intelligence (AI) to enhance their services and provide more efficient and personalized experiences to users. This paper explores the role of AI in library services, focusing on its applications and impact. The present article begins by discussing the integration of AI technologies such as natural language processing, machine learning, and knowledge graphs in library systems. It then examines the benefits of AI, including improved information retrieval, recommendation systems, virtual assistants, and data analytics. Ethical considerations related to AI in libraries are also addressed. The paper highlights the challenges and future directions for AI implementation, including the need for training of librarians and the importance of user acceptance. The paper contributes to a better understanding of the opportunities and challenges associated with leveraging AI in library services, ultimately paving the way for more effective and user-centric library experiences.

Indexing Excellence: Best Practices in Library Abstracting for Information Retrieval

Indexing and abstracting play pivotal roles in organizing and retrieving information within libraries. This paper delves into the intricate landscape of optimal indexing practices and their profound implications on the efficiency of information retrieval systems. By scrutinizing the methodologies employed in creating high-quality abstracts, this study aims to shed light on their substantial influence on the accessibility and usability of information resources within library collections. The investigation focuses on the multifaceted aspects of indexing excellence, exploring its direct correlation with improved information retrieval mechanisms. It examines in detail the methodologies, standards, and tools utilized in the creation and application of high-quality abstracts. Furthermore, it critically evaluates the utilization of controlled vocabularies and adherence to established indexing guidelines, highlighting their indispensable roles in ensuring the precision and relevance of indexed content. Analyzing the intersection of indexing practices and their impact on information retrieval, this study aims to provide valuable insights into enhancing the efficacy of library abstracting. Recognizing the importance of streamlined access to information resources, this research endeavors to contribute to the continual evolution of information science and user-centered library services.

Deep Learning Algorithms for Personalized Services and Enhanced User Experience in Libraries

The integration of deep learning (DL) algorithms in library settings engenders a multitude of challenges and complexities, encompassing unintended ramifications, ethical quandaries, a dearth of specialized literature elucidating DL in library contexts, the intricacies of dataset selection and human intervention, and the inherent limitations when juxtaposed with the remarkable cognitive capabilities of the human brain. To surmount these hurdles and attain a profound comprehension of DL in library settings, a rigorous and comprehensive systematic literature review (SLR) becomes imperative. This study investigates the application of DL algorithms in examining user-seeking behaviour to provide personalized services and enhance user experience in libraries. Through a comprehensive literature review, the study aims to uncover the benefits, challenges, and implications of integrating DL algorithms for user behaviour analysis and personalized services in library environments. The investigation encompasses a systematic literature review, employing a meticulous search and screening process utilizing the Scopus database. DL algorithms enable tailored recommendations, resource suggestions, and personalized search outcomes, improving information retrieval and user-centric services. Ethical considerations and ongoing research are emphasized to address challenges and maximize the potential of DL algorithms in libraries. The integration of DL algorithms in libraries yields substantial benefits, including improved information retrieval capabilities, augmented resource recommendation systems, and the delivery of user-centric services. The paper offers valuable insights to researchers, practitioners, and stakeholders operating within this field.

Handling Large-Scale Document Collections using Information Retrieval in the Age of Big Data

This paper's primary goal is to present an overview of big data and its analysis utilizing various methodologies, particularly evolutionary computing techniques, which improve information retrieval over standard search methods. is obtainable. Big data is defined as a huge, diverse collection of data that is difficult to handle with conventional computational methods and necessitates the use of more sophisticated statistical approaches in order to extract pertinent information from the data. Along with providing an overview of evolutionary computational approaches, this study also discusses some of the main models used for information retrieval.

Migration Misadventures: The Challenges of Creating an Inter-Institutional Migration Plan

Archival institution migration projects are planned data transfers from existing data formats to more accessible formats that assist in preserving transferred data, improving information retrieval, and preventing obsolescence. Various archival institutions are increasingly planning migration projects because current technology makes the process easier and more affordable than in the past. In this proceeding, I will walk through the planning stages and associated challenges of NASA’s inter-institutional migration plan, Archival Description Center Migration Plans Project, which is part of a larger reorganization of the archives’ functional area to an Enterprise program. For this project, we utilized the open-source, standards-based, web-based applications Access to Memory and Archivematica. At the current project stage, we have collaborated with archivists from seven of the eleven existing NASA archive centers. One of the goals of this Enterprise reorganization is to facilitate cross-collection search and discovery and establish cross-institution metadata standards.

The road from manual to automatic semantic indexing of biomedical literature: a 10 years journey.

Biomedical experts are facing challenges in keeping up with the vast amount of biomedical knowledge published daily. With millions of citations added to databases like MEDLINE/PubMed each year, efficiently accessing relevant information becomes crucial. Traditional term-based searches may lead to irrelevant or missed documents due to homonyms, synonyms, abbreviations, or term mismatch. To address this, semantic search approaches employing predefined concepts with associated synonyms and relations have been used to expand query terms and improve information retrieval. The National Library of Medicine (NLM) plays a significant role in this area, indexing citations in the MEDLINE database with topic descriptors from the Medical Subject Headings (MeSH) thesaurus, enabling advanced semantic search strategies to retrieve relevant citations, despite synonymy, and polysemy of biomedical terms. Over time, advancements in semantic indexing have been made, with Machine Learning facilitating the transition from manual to automatic semantic indexing in the biomedical literature. The paper highlights the journey of this transition, starting with manual semantic indexing and the initial efforts toward automatic indexing. The BioASQ challenge has served as a catalyst in revolutionizing the domain of semantic indexing, further pushing the boundaries of efficient knowledge retrieval in the biomedical field.

DUOINSPECT- Uncovering Duplicates through Powerful Model of Random Forest and XGBoost Classifier

Duplicate question pair detection plays a vital role in improving information retrieval systems and enhancing user experience. In this paper, we present a comprehensive study on duplicate question pair detection utilizing the Quora dataset. We employed machine learning techniques, specifically Random Forest and XGBoost classifiers, to develop accurate models for identifying duplicate question pairs. To improve the performance of the models, we introduced additional features to the dataset, augmenting the original data. By incorporating 22 extra features derived from the raw data, we aimed to capture more nuanced patterns and increase the models' discriminatory power. The Random Forest model achieved a significant improvement, with a performance boost to 89.4% accuracy compared to the initial 73% accuracy. The XGBoost classifier also showed promising results, achieving an accuracy of 73.4% initially and 79.2% after incorporating the additional features. This paper serves as a valuable reference for researchers and practitioners interested in the field of duplicate question pair detection. The findings highlight the effectiveness of Random Forest and XGBoost classifiers in combination with additional features for improving accuracy in this task. The web application provides a practical and user-friendly tool for real- time duplicate question pair detection, offering potential applications in information retrieval systems, chatbots, and question-answering platforms. Key Words: Question Pair Similarity; XGBoost, Random Forest, Machine Learning.

Improving the Performance of Searchable Symmetric Encryption by Optimizing Locality

Both individuals and organizations prioritize data security and privacy, leading to an increasing focus on technological solutions that emphasize these aspects. Searchable symmetric encryption stands out as a prominent choice for secure storage and search of encrypted data on cloud servers, contributing to this objective. While searchable symmetric encryption offers numerous benefits, it also faces certain challenges, particularly when dealing with large databases. One significant challenge is poor performance, often attributed to poor locality. Visiting multiple locations can significantly increase the time required for data retrieval. Additionally, optimization methods aimed at improving locality can sometimes impact read efficiency or result in excessive storage of the encrypted index on the cloud server. In this paper, we present a scheme that effectively addresses these issues. We have enhanced the encrypted inverted index storage mechanism to improve information retrieval performance. Our scheme achieves optimal locality O(1) and optimal read efficiency in O(1), resulting in a significant increase in retrieval speed. Through experimentation with real-world data, we have demonstrated the practicality, accuracy, and security of our scheme.

Improving Semantic Information Retrieval Using Multinomial Naive Bayes Classifier and Bayesian Networks

This research proposes a new approach to improve information retrieval systems based on a multinomial naive Bayes classifier (MNBC), Bayesian networks (BNs), and a multi-terminology which includes MeSH thesaurus (Medical Subject Headings) and SNOMED CT (Systematized Nomenclature of Medicine of Clinical Terms). Our approach, which is entitled improving semantic information retrieval (IMSIR), extracts and disambiguates concepts and retrieves documents. Relevant concepts of ambiguous terms were selected using probability measures and biomedical terminologies. Concepts are also extracted using an MNBC. The UMLS (Unified Medical Language System) thesaurus was then used to filter and rank concepts. Finally, we exploited a Bayesian network to match documents and queries using a conceptual representation. Our main contribution in this paper is to combine a supervised method (MNBC) and an unsupervised method (BN) to extract concepts from documents and queries. We also propose filtering the extracted concepts in order to keep relevant ones. Experiments of IMSIR using the two corpora, the OHSUMED corpus and the Clinical Trial (CT) corpus, were interesting because their results outperformed those of the baseline: the P@50 improvement rate was +36.5% over the baseline when the CT corpus was used.

XML CLUSTERING FRAMEWORK BASED ON DOCUMENT CONTENT AND STRUCTURE IN A HETEROGENEOUS DIGITAL LIBRARY

As textually published information is increasing in digital libraries, efficient retrieval methods are required. Textual documents in a digital library are available in various structures and contents. It is possible to represent these documents with hierarchical levels of granularity when these are organized in XML structure to improve precision by focused retrieval. By this means, contextual elements of each document can be retrieved from a known structure. One solution for retrieving these elements is clustering from a combination of Content and Structural similarities. To achieve this, a novel two-level clustering framework based on Content and Structure is proposed. The framework decomposes a document into meaningful structural units and analyzes all its rich text in its own structure. The quality of the proposed framework was experimented on a heterogeneous XML document collection, having varieties of data sources, structures, and content, be represented as a sample of a real digital library. This collection was made with capabilities to test all of our objectives. The clustering results were evaluated by the Entropy criterion. Finally, the Content and Structure clustering was compared with the usual clustering based on the Content Only to prove the efficacy of considering structural features against the existing Content Only methods in the retrieval process. The total Entropy results of the two-level Content and Structural clustering are almost twice better than the Content Only clustering approach. Consequently, the proposed framework has the ability to improve Information Retrieval systems from two points of view: i) considering the structural aspect of text-rich documents in the retrieval process, and ii) replacing the document-level retrieval with the element-level retrieval.

From STEM to 4D STEM: Ultrafast Diffraction Mapping with a Hybrid-Pixel Detector

Abstract4D scanning transmission electron microscope (STEM) techniques have been increasingly featured among the electron microscopy characterization approaches, as they provide a perspective of improved information retrieval from samples overall. To make 4D STEM experiments as viable as conventional STEM image acquisition, the recording of diffraction patterns with a pixelated detector at fast frame rates, sufficient sensitivity to capture single electron hits, and high dynamic range is necessary. This paper addresses the recent development in hybrid-pixel detector technology that now allows 4D STEM experiments with a similar setup to conventional STEM imaging with pixel collection time under 10 µs. Application examples on virtual STEM detectors and crystal phase-orientation mapping are presented.

The indexing policy in the practices of Brazilian institutional repositories: A diagnostic study from the perception of managers and indexers

Institutional repositories aim to gather, treat and disseminate information resources produced in a given institution. The adoption of an indexing policy aims to improve information retrieval by the user community of the institutional repository, by proposing elements that standardize the practices of librarians who work in subject cataloging. The objective of the research is to analyze the perception of managers and indexers of Brazilian institutional repositories about the indexing policy for information organization and representation, with the specific objectives of performing a compared evaluation of elements and variables (characteristics, processes, and instruments) of the indexing policy regarding indexing and retrieval, discussion of vocabulary control procedures, and obtaining an overview focusing on the perception of the need for an indexing policy in Brazilian institutional repositories. Semi-structured interviews were applied to nine participants from eight institutional repositories to investigate the requirements, elements and variables of the indexing policy in the practice of managers and librarians of institutional repositories. The results reveal the need for improvements in the practices of the analyzed institutional repositories regarding the activities of subject cataloging, standardization of subject metadata, and vocabulary control, queries, and in carrying out tests or trials for continuous evaluation of indexing and information retrieval with users. The study also revealed that this scenario can be more positive if institutional repositories adopt an indexing policy for the practices they perform in repositories to be understood by managers and librarians as a tool to improve information retrieval. La política de indización en las prácticas de los repositorios institucionales brasileños: un estudio de diagnóstico desde la percepción de gestores e indexadores

A Technology Watch/Competitive Intelligence–based Decision-Support System optimised with Genetic Algorithms

To survive and prosper in a highly competitive environment where uncertainty and ambiguity are the norm, today’s firms are faced with the need for new information management methods and tools. Two of the most prominent strategies that take information and its treatment as a value-generating element in firms’ decision-making are Technology Watch and Competitive Intelligence. In addition, one of the fundamental components that a system based on these strategies must have is an efficient method of Information Retrieval. The present study describes a Competitive Intelligence–based decision-support system that uses a Genetic Algorithm. The system contributes to improving information retrieval through search optimisation, thus enhancing the performance of this knowledge-generating tool for organisations.

User Interface Features and Knowledge Organisation Systems in Institutional Repositories A Case Study of Centrally Funded Technical Institutions in India

Institutional Repositories (IRs) are effective systems for managing and disseminating institutions’ in scholarly communication. More specifically, an IR enhances the visibility and discoverability of the content and validates the repository’s importance. Knowledge Organisation System (KOS) strengthens the digital content organisation, connects users with collections, and improves information retrieval functionalities. This paper investigates the present status of user interface features and incorporates KOS in the institutional repository of technical institutions, restricted to Centrally Funded Technical Institutions in India. A group of twenty-four web-accessible institutional repositories was identified, and their KOS and user interface features were evaluated. It was found that user interfaces of all IRs under study comply with essential search and navigation functionalities, such as simple and advanced search, browsing, faceted or filtering approaches, and integration with multiple KOS. Only a few of them include complex KOS, such as control vocabulary. All repositories show their search results in both normal-text and metadata views. Some have specific display features, such as highlighting the query or displaying a thumbnail. Google is one of the most popular search engines that indexes IR content for visibility and discoverability, and approximately 90 per cent of repositories are linked with NDLI. Global visibility and impact participation are moderate, and they require attention.

Reliability of real-world data for diagnosis of metastatic prostate cancer.

397 Background: Real-world data (RWD) is playing an increasingly important role in cancer research. Surrogate endpoints such as metastasis-free survival play an important role in prostate cancer research, leading to interest in its computational extraction, typically with use of International Classification of Disease (ICD) metastatic codes. While prior studies have suggested that ICD codes are valid for identification of patients (pts) with metastatic prostate cancer (MPC), delays in coding may impact their accuracy. The objective of this informatics-based study is to quantify the time delay between diagnosis of MPC and entry of ICD MPC-related code and its interaction with changing institutional healthcare processes. Methods: A single institutional EHR data warehouse was queried to identify a random sample of 100 pts with MPC diagnosis based on ICD codes (ICD10 C79 or ICD9 198.5) from 2013-2021 who were also seen in the genitourinary medical oncology program (GUMOP). Of note, in 6/2018, the GUMOP adopted EHR-specific MPC visit diagnosis identifiers (Dx ID) to improve MPC coding during clinic independent of ICD codes typically used by RWD researchers. Thus, the study cohort was designed to include pts whose first follow up after being diagnosed with MPC was before (n = 50) or after (n = 50) Dx ID implementation. Date of first MPC ICD code entry at any point in the EHR was compared against true date of MPC, based on physician review of definitive imaging or pathology. Data analysis was performed with Wilcox Signed rank test, bivariate analyses, and multivariable linear regression. Covariates included modality of diagnosis confirmation and timing with Dx ID implementation. Results: One hundred pts with MPC ICD coded in the EHR were included, with 29 pts diagnosed by PSMA PET and 71 by conventional imaging. Median time from true MPC diagnosis to first subsequent clinic follow up was < 1 month (IQR 0-2), while median time from true MPC diagnosis to entry of ICD MPC-related code was longer at 4mo (IQR 0-15). 5 pts had C79 applied for N1 disease and 10 pts for work-up of biochemical recurrence. On multivariable analysis of potential factors affecting time interval to MPC ICD entry, Dx ID implementation (b = -6.5 mo [95% CI -1.8 to -11.2], p = 0.007) and non-PSMA based diagnosis (b = -5.7 mo [95% CI -0.5 to -10.8], p = 0.03) were independently associated with shorter time to ICD coding. In subset analysis of the cohort after Dx ID implementation, use of both ICD and Dx ID to identify pts with MPC reduced the median time from true MPC diagnosis to EHR coding (1mo, IQR 0-6.3) compared to ICD alone (2mo, IQR 0-8) (p = 0.003). Conclusions: Timing of MPC ICD entry is highly variable and may carry biases derived from healthcare processes, including data entry and diagnostic testing. This may be improved with EHR workflow interventions. It is essential to have domain knowledge of clinical coding practices to improve information retrieval and recognize potential limitations and biases.

Machine Learning for Arabic Text Classification: A Comparative Study

The ultimate aim of Machine Learning (ML) is to make machine acts like a human. In particular, ML algorithms are widely used to classify texts. Text classification is the process of classifying texts into a predefined set of categories based on the texts’ content. It contributes to improving information retrieval on the Web. In this paper, we focus on the "Arabic" text classification since there is a large community in the world that uses this language. The Arabic text classification process consists of three main steps: preprocessing, feature extraction and ML algorithm. This paper presents a comparative empirical study to see which combination (feature extraction - ML algorithm) acts well when dealing with Arabic documents. So, we implemented one hundred sixty classifiers by combining 5 feature extraction techniques and 32 machine learning algorithms. Then, we made these classifiers open access for the benefit of the AI and NLP communities. Experiments were carried out using a huge open dataset. The comparison study reveals that TFIDF-Perceptron is the best performing combination of a classifier.

Improving Biomedical Information Retrieval with Neural Retrievers

Information retrieval (IR) is essential in search engines and dialogue systems as well as natural language processing tasks such as open-domain question answering. IR serve an important function in the biomedical domain, where content and sources of scientific knowledge may evolve rapidly. Although neural retrievers have surpassed traditional IR approaches such as TF-IDF and BM25 in standard open-domain question answering tasks, they are still found lacking in the biomedical domain. In this paper, we seek to improve information retrieval (IR) using neural retrievers (NR) in the biomedical domain, and achieve this goal using a three-pronged approach. First, to tackle the relative lack of data in the biomedical domain, we propose a template-based question generation method that can be leveraged to train neural retriever models. Second, we develop two novel pre-training tasks that are closely aligned to the downstream task of information retrieval. Third, we introduce the ``Poly-DPR'' model which encodes each context into multiple context vectors. Extensive experiments and analysis on the BioASQ challenge suggest that our proposed method leads to large gains over existing neural approaches and beats BM25 in the small-corpus setting. We show that BM25 and our method can complement each other, and a simple hybrid model leads to further gains in the large corpus setting.