Search

Pseudo relevance feedback (PRF) is a powerful query expansion (QE) technique that prepares queries using the top k pseudo-relevant documents and choosing expansion elements. Traditional PRF frameworks have robustly handled vocabulary mismatch corresponding to user queries and pertinent documents; nevertheless, expansion elements are chosen, disregarding similarity to the original query’s elements. Word embedding (WE) schemes comprise techniques of significant interest concerning QE, that falls within the information retrieval domain. Deep averaging networks (DANs) defines a framework relying on average word presence passed through multiple linear layers. The complete query is understandably represented using the average vector comprising the query terms. The vector may be employed for determining expansion elements pertinent to the entire query. In this study, we suggest a DANs-based technique that augments PRF frameworks by integrating WE similarities to facilitate Arabic information retrieval. The technique is based on the fundamental that the top pseudo-relevant document set is assessed to determine candidate element distribution and select expansion terms appropriately, considering their similarity to the average vector representing the initial query elements. The Word2Vec model is selected for executing the experiments on a standard Arabic TREC 2001/2002 set. The majority of the evaluations indicate that the PRF implementation in the present study offers a significant performance improvement compared to that of the baseline PRF frameworks.

Recommender Systems have gained immense popularity due to their capability of dealing with a massive amount of information in various domains. They are considered information filtering systems that make predictions or recommendations to users based on their interests and preferences. The more recent technology, Linked Open Data (LOD), has been introduced, and a vast amount of Resource Description Framework data have been published in freely accessible datasets. These datasets are connected to form the so-called LOD cloud. The need for semantic data representation has been identified as one of the next challenges in Recommender Systems. In a LOD-enabled recommendation framework where domain awareness plays a key role, the semantic information provided in the LOD can be exploited. However, dealing with a big chunk of the data from the LOD cloud and its integration with any domain datasets remains a challenge due to various issues, such as resource constraints and broken links. This paper presents the challenges of interconnecting and extracting the DBpedia data with the MovieLens 1 Million dataset. This study demonstrates how LOD can be a vital yet rich source of content knowledge that helps recommender systems address the issues of data sparsity and insufficient content analysis. Based on the challenges, we proposed a few alternatives and solutions to some of the challenges.

There has been a growing interest in halal-related ontology research in recent years, as ontology has gained recognition in the halal industry. This paper discusses the development of a flavouring ontology that will assist halal management auditors in predicting the halal status of flavours in order to process food producers’ applications for halal certification. The development of a flavouring ontology is based on multiple references, because the auditors of halal management divisions must consult a variety of sources independently in order to determine the halal status of flavourings. The process includes 1) determining the ontology goal and scope, 2) building ontologies, and 3) evaluating the ontologies. The researcher used Protégé to design the ontologies, and Phyton was used to develop a prototype based on flavouring ontology. The developed ontology consists of four classes, nine sub-classes, and 11 relationships. The evaluation of the ontology using the prototype revealed that the majority of experts were satisfied with the information generated by the ontology in the prototype, particularly in relation to synonyms and the hierarchical structure of a flavour. However, the experts suggest improvements in terms of flavour metadata, especially on raw materials and natural occurrence data, so that the flavour information retrieved is comprehensive and accurate. [ABSTRACT FROM AUTHOR]

Content-based (CB) recommendation algorithms recommend items to a user based on items the user liked in the past. CB methodologies have gained attention due to their higher accuracy and transparency and the emergence of new technologies, such as knowledge graphs (KGs), advances in natural language processing (NLP), and sentiment analysis. While most previous studies have mainly focussed on the use of term frequency-inverse document frequency (TF-IDF) and other related enhancements, little work can be found on using KGs in CB recommendations. This paper presents an enhancement of the conventional CB recommendation by incorporating KGs for a movie domain. The graph is constructed using the MovieLens data set, which is augmented with additional features such as actors, directors, and genres. Furthermore, the graph is expanded by incorporating topics derived from latent dirichlet allocation (LDA) extraction. Using the KGs, the proposed approach enhances user profiles by leveraging the interconnected user-movie relationship within a graph structure. The results of the experiments showed that the proposed approach exceeded the tested baselines in terms of precision, recall, and F-score metrics. [ABSTRACT FROM AUTHOR]

The adoption of information and communication technology (ICT) by older adults with cognitive frailty and impairment is beneficial to support aging in place and promote healthy aging. However, data are scarce regarding the use of ICT by this demographic in comparison with other age groups. This bibliometric analysis was aimed at systematically mapping the literature on ICT‐related research on older adults with cognitive frailty and cognitive impairment to provide insights into research trends, patterns and knowledge gaps. Data were extracted from the Web of Science database, which identified 324 publications between 1980 and 2023. Performance analysis and science mapping were carried out using Microsoft® Excel, VOSViewer and Harzing's Publish or Perish. The analysis showed an upsurge in the research output trend over time. Notable journals, authors, citations, nations and research areas have been documented. Four key clusters were identified, including: (i) caregiver concern, support and involvement; (ii) technology as a tool for cognitive training and cognitive rehabilitation; (iii) cognitive improvement; and (iv) the use of technology for prevention and self‐management. The findings derived from this analysis provide an appropriate reference for future researchers to bridge the gap in ICT‐related studies among this population, and distinguish the relevant articles that are required for further investigation. These include the need for further long‐term research, the incorporation of ICT‐based approaches to counter cognitive frailty and the importance of multidomain telehealth interventions. Geriatr Gerontol Int 2024; 24: 251–262. [ABSTRACT FROM AUTHOR]

One of the main issues associated with search engines is the query–document vocabulary mismatch problem, a long-standing problem in Information Retrieval (IR). This problem occurs when a user query does not match the content of stored documents, and it affects most search tasks. Automatic query expansion (AQE) is one of the most common approaches used to address this problem. Various AQE techniques have been proposed; these mainly involve finding synonyms or related words for the query terms. Word embedding (WE) is one of the methods that are currently receiving significant attention. Most of the existing AQE techniques focus on expanding the individual query terms rather the entire query during the expansion process, and this can lead to query drift if poor expansion terms are selected. In this article, we introduce Deep Averaging Networks (DANs), an architecture that feeds the average of the WE vectors produced by the Word2Vec toolkit for the terms in a query through several linear neural network layers. This average vector is assumed to represent the meaning of the query as a whole and can be used to find expansion terms that are relevant to the complete query. We explore the potential of DANs for AQE in Arabic document retrieval. We experiment with using DANs for AQE in the classic probabilistic BM25 model as well as for two recent expansion strategies: Embedding-Based Query Expansion approach (EQE1) and Prospect-Guided Query Expansion Strategy (V2Q). Although DANs did not improve all outcomes when used in the BM25 model, it outperformed all baselines when incorporated into the EQE1 and V2Q expansion strategies. [ABSTRACT FROM AUTHOR]

Today, social media sites like Twitter provide effective platforms to share opinions and thoughts in public with millions of other users. These opinions shared on such sites influence a large number of people who may easily retweet them and accelerate their spread. Unfortunately, some of these opinions were expressed by extremists who promoted hateful content. Since Arabic is one of the most spoken languages, it is crucial to automate the process of monitoring Arabic content published on social sites. Therefore, this study aims to propose a hybrid technique to detect extremism in Arabic social media texts and articles to monitor the situation of published extremist content. The proposed technique combines the lexicon-based approach with the rough set theory approach. The rough set theory is employed with two approximation strategies: lower approximation and accuracy approximation. The hybrid technique used the rough set theory as a classifier and the lexicon-based as a vector. Furthermore, this study built three types of corpuses (V1, V2, and V3) collected from Twitter. The experimental findings show that among the proposed hybrid methods, the accuracy approximation was superior to the lower approximation with seed vector. It was also revealed that hybrid methods outperformed machine learning techniques in terms of efficiency. Moreover, the study recommends using an accuracy approximation method with seed vector to identify the polarity of the text. [ABSTRACT FROM AUTHOR]