Search results

Question answering (QA) answers the questions asked by people in the form of natural language. In the QA, due to the subjectivity of users, the questions they query have different expressions, which increases the difficulty of text retrieval. Therefore, the purpose of this paper is to explore new query rewriting method for QA that integrates multiple related questions (RQs) to form an optimal question. Moreover, it is important to generate a new dataset of the original query (OQ) with multiple RQs.

This study collects a new dataset SQuAD_extend by crawling the QA community and uses word-graph to model the collected OQs. Next, Beam search finds the best path to get the best question. To deeply represent the features of the question, pretrained model BERT is used to model sentences.

The experimental results show three outstanding findings. (1) The quality of the answers is better after adding the RQs of the OQs. (2) The word-graph that is used to model the problem and choose the optimal path is conducive to finding the best question. (3) Finally, BERT can deeply characterize the semantics of the exact problem.

The proposed method can use word-graph to construct multiple questions and select the optimal path for rewriting the question, and the quality of answers is better than the baseline. In practice, the research results can help guide users to clarify their query intentions and finally achieve the best answer.

This study aims to look at challenges that hinder small- and medium-sized enterprises (SMEs) from using open data (OD). The research gaps identified are then used to propose a next generation of OD platform (ODP+).

This study proposes a more effective platform for SMEs called ODP+. A proof of concept was implemented by using modern techniques and technologies, with a pilot conducted among selected SMEs and government employees to test the approach’s viability.

The findings identify current OD platforms generally, and in Gulf Cooperation Council (GCC) countries, they encounter several difficulties, including that the data sets are complex to understand and determine their potential for reuse. The application of big data analytics in mitigating the identified challenges is demonstrated through the artefacts that have been developed.

This paper discusses several challenges that must be addressed to ensure that OD is accessible, helpful and of high quality in the future when planning and implementing OD initiatives.

The proposed ODP+ integrates social network data, SME data sets and government databases. It will give SMEs a platform for combining data from government agencies, third parties and social networks to carry out complex analytical scenarios or build the needed application using artificial intelligence.

The findings promote the potential future utilisation of OD and suggest ways to give users access to knowledge and features.

To the best of the authors’ knowledge, no study provides extensive research about OD in Qatar or GCC. Further, the proposed ODP+ is a new platform that allows SMEs to run natural language data analytics queries.

Generative AI and more specifically ChatGPT has brought a revolution in the lives  of people by providing them with required knowledge that it has learnt from an exponentially large knowledge base. In this viewpoint, we are initiating the debate and offer the first step towards Generative AI based knowledge management systems in organizations.

This study is a viewpoint and develops a conceptual foundation using existing literature on how ChatGPT can enhance the KM capability based on Nonaka’s SECI model. It further supports the concept by collecting data from a public sector univesity in Hong Kong to strenghten our argument of ChatGPT mediated knowledge management system.

We posit that all four processes, that is Socialization, Externalization, Combination and Internalization can significantly improve when integrated with ChatGPT. ChatGPT users are, in general, satisfied with the use of ChatGPT being capable of facilitating knowledge generation and flow in organizations.

The study provides a conceptual foundation to further the knowledge on how ChatGPT can be integrated within organizations to enhance the knowledge management capability of organizations. Further, it develops an understanding on how managers and executives can use ChatGPT for effective knowledge management through improving the four processes of Nonaka’s SECI model.

This is one of the earliest studies on the linkage of knowledge management with ChatGPT and lays a foundation for ChatGPT mediated knowledge management system in organizations.

Safety management plays an important part in coal mine construction. Due to complex data, the implementation of the construction safety knowledge scattered in standards poses a challenge. This paper aims to develop a knowledge extraction model to automatically and efficiently extract domain knowledge from unstructured texts.

Bidirectional encoder representations from transformers (BERT)-bidirectional long short-term memory (BiLSTM)-conditional random field (CRF) method based on a pre-training language model was applied to carry out knowledge entity recognition in the field of coal mine construction safety in this paper. Firstly, 80 safety standards for coal mine construction were collected, sorted out and marked as a descriptive corpus. Then, the BERT pre-training language model was used to obtain dynamic word vectors. Finally, the BiLSTM-CRF model concluded the entity’s optimal tag sequence.

Accordingly, 11,933 entities and 2,051 relationships in the standard specifications texts of this paper were identified and a language model suitable for coal mine construction safety management was proposed. The experiments showed that F1 values were all above 60% in nine types of entities such as security management. F1 value of this model was more than 60% for entity extraction. The model identified and extracted entities more accurately than conventional methods.

This work completed the domain knowledge query and built a Q&A platform via entities and relationships identified by the standard specifications suitable for coal mines. This paper proposed a systematic framework for texts in coal mine construction safety to improve efficiency and accuracy of domain-specific entity extraction. In addition, the pretraining language model was also introduced into the coal mine construction safety to realize dynamic entity recognition, which provides technical support and theoretical reference for the optimization of safety management platforms.

This paper aims to explore ChatGPT’s (generative pre-trained transformers) potential as a tool for retailers to improve customer experience and boost sales. While it provides benefits like personalized recommendations and 24/7 assistance, there are limitations, like difficulty in understanding unconventional language. The paper stresses careful integration to overcome these limitations and create a better customer experience. Additionally, it discusses the potential for further development and integration of ChatGPT in retail, such as generating product descriptions and virtual try-on experiences. Finally, the paper encourages retailers to embrace ChatGPT to meet their customer needs.

Case-based methodology involves using specific cases or examples to explore a broader issue or phenomenon. Researchers have analysed real-world cases to identify patterns, themes and insights that can be applied to other contexts or situations. This was useful for understanding complex and multifaceted issues as it allowed us to delve deeper into specific examples and explore the nuances of the situation.

While ChatGPT is a powerful tool for retailers, limitations such as difficulty in understanding non-standard accents and unconventional language can arise, causing customer frustration. Retail managers must integrate ChatGPT in a way that enhances customer experience. In the future, ChatGPT has the potential to generate product descriptions, provide virtual try-on experiences and integrate with augmented or virtual reality technology to offer more immersive experiences. Careful consideration and integration can help retailers overcome these limitations and offer personalized recommendations, round-the-clock assistance and an engaging customer experience that improves sales.

The case topic is very much in a novel stage of research and writing.

This paper evaluates the precision of four metasearch engines (MSEs) – DuckDuckGo, Dogpile, Metacrawler and Startpage, to determine which metasearch engine exhibits the highest level of precision and to identify the metasearch engine that is most likely to return the most relevant search results.

The research is divided into two parts: the first phase involves four queries categorized into two segments (4-Q-2-S), while the second phase includes six queries divided into three segments (6-Q-3-S). These queries vary in complexity, falling into three types: simple, phrase and complex. The precision, average precision and the presence of duplicates across all the evaluated metasearch engines are determined.

The study clearly demonstrated that Startpage returned the most relevant results and achieved the highest precision (0.98) among the four MSEs. Conversely, DuckDuckGo exhibited consistent performance across both phases of the study.

The study only evaluated four metasearch engines, which may not be representative of all available metasearch engines. Additionally, a limited number of queries were used, which may not be sufficient to generalize the findings to all types of queries.

The findings of this study can be valuable for accreditation agencies in managing duplicates, improving their search capabilities and obtaining more relevant and precise results. These findings can also assist users in selecting the best metasearch engine based on precision rather than interface.

The study is the first of its kind which evaluates the four metasearch engines. No similar study has been conducted in the past to measure the performance of metasearch engines.

The paper aims to provide a comprehensive analysis of artificial intelligence’s (AI) transformative impact on the real estate industry. By examining various AI applications, from property recommendations to compliance automation, this study highlights potential benefits such as increased accuracy and efficiency. At the same time, this study critically discusses potential drawbacks, like privacy concerns and job displacement. The paper's goal is to offer valuable insights to industry professionals and policy makers, aiding strategic decision-making as AI continues to reshape the landscape of the real estate sector.

This paper employs an extensive literature review, combined with a qualitative analysis of case studies. Various AI applications in the real estate industry are examined, including machine learning for property recommendations and valuation, VR/AR property tours, AI automation for contract and regulatory compliance, and chatbots for customer service. The study also delves into the optimisation potential of AI in building management, lead generation, and risk assessment, whilst critically discussing potential challenges such as data privacy, algorithmic bias, and job displacement. The outcomes aim to inform strategic decisions for industry professionals and policy makers.

The study finds that AI has significant potential to revolutionise the real estate industry through enhanced accuracy in property valuation, efficient automation and immersive AR/VR experiences. AI-driven chatbots and optimisation in building management also hold promise. However, this study also uncovers potential challenges, including data privacy issues, algorithmic biases, and possible job displacement due to increased automation. The insights gleaned from this study underscore the importance of strategic decision-making in harnessing the benefits of AI while mitigating potential drawbacks in the real estate sector.

The paper's practical implications extend to industry professionals, policy makers, and technology developers. Professionals gain insights into how AI can enhance efficiency and accuracy in the real estate sector, guiding strategic decision-making. For policy makers, understanding potential challenges like data privacy and job displacement informs regulatory measures. Technology developers can also benefit from understanding the sector-specific applications and concerns raised. Additionally, highlighting the need for addressing algorithmic bias and privacy concerns in AI systems may foster better design practices. Therefore, the paper's findings could significantly shape the future trajectory of AI integration in real estate.

The paper provides original value by offering a comprehensive analysis of the transformative impact of AI in the real estate industry. Its multi-faceted examination of AI applications, coupled with a critical discussion on potential challenges, provides a balanced perspective. The paper's focus on informing strategic decisions for professionals and policy makers makes it a valuable resource. Moreover, by considering both benefits and drawbacks, this study contributes to the discourse on AI's broader societal implications. In the context of rapid technological change, such comprehensive studies are rare, adding to the paper's originality.

This study addresses how algorithmic recommendations and their affordances shape everyday information practices among young people.

Thematic interviews were conducted with 20 Finnish young people aged 15–16 years. The material was analysed using qualitative content analysis, with a focus on everyday information practices involving online platforms.

The key finding of the study is that the current affordances of algorithmic recommendations enable users to engage in more passive practices instead of active search and evaluation practices. Two major themes emerged from the analysis: enabling not searching, inviting high trust, which highlights the how the affordances of algorithmic recommendations enable the delegation of search to a recommender system and, at the same time, invite trust in the system, and constraining finding, discouraging diversity, which focuses on the constraining degree of affordances and breakdowns associated with algorithmic recommendations.

This study contributes new knowledge regarding the ways in which algorithmic recommendations shape the information practices in young people's everyday lives specifically addressing the constraining nature of affordances.

The purpose of this paper is to discuss how retracted scientific papers become zombie papers and why they are problematic and to encourage librarians to become active in addressing these problems.

This paper explains what zombie papers are, how they are created and the potential impact they can have on the body of scientific literature. It explains how and why they are different than other common types of misleading scientific publications. It also explores recent developments such as the growth of artificial intelligence (AI) technologies and changes to organizations that make data about paper retractions available.

While journal retractions are as old as scientific publishing itself, the seriousness of retractions persisting and being used in the body of scientific literature has recently been recognized as a serious concern. The rise of new AI technologies such as ChatGPT has made the presence of zombie papers in the data used to train large language models (LLMs) extremely concerning.

While librarians are well-aware of journal retractions and most include information about them in their information literacy training, concerns around zombie papers and their potential presence in the data used to train LLMs will likely be a new consideration for most.

This study investigates whether and how the service quality of artificial intelligence (AI) chatbots affects customer loyalty to an organization.

Based on the sequential chain model of service quality loyalty, this study first classifies AI chatbot service quality into nine attributes and then develops a research model to explore the internal mechanism of how AI chatbot service quality affects customer loyalty. The analysis of survey data from 459 respondents provided insights into the interrelationships among AI chatbot service quality attributes, perceived value, cognitive and affective trust, satisfaction and customer loyalty.

The results show that AI chatbot service quality positively affects customer loyalty through perceived value, cognitive trust, affective trust and satisfaction.

This study captures the attributes of the service quality of AI chatbots and reveals the significant influence of service quality on customer loyalty. This study develops research on service quality in the information system (IS) field and extends the sequential chain model of quality loyalty to the context of AI services. The findings not only help an organization find a way to improve customers' perceived value, trust, satisfaction and loyalty but also provide guidance in the development, adoption, and post-adoption stages of AI chatbots.