Search results

In the era of big data, various industries are generating large amounts of text data every day. Simplifying and summarizing these data can effectively serve users and improve efficiency. Recently, zero-shot prompting in large language models (LLMs) has demonstrated remarkable performance on various language tasks. However, generating a very “concise” multi-document summary is a difficult task for it. When conciseness is specified in the zero-shot prompting, the generated multi-document summary still contains some unimportant information, even with the few-shot prompting. This paper aims to propose a LLMs prompting for multi-document summarization task.

To overcome this challenge, the authors propose chain-of-event (CoE) prompting for multi-document summarization (MDS) task. In this prompting, the authors take events as the center and propose a four-step summary reasoning process: specific event extraction; event abstraction and generalization; common event statistics; and summary generation. To further improve the performance of LLMs, the authors extend CoE prompting with the example of summary reasoning.

Summaries generated by CoE prompting are more abstractive, concise and accurate. The authors evaluate the authors’ proposed prompting on two data sets. The experimental results over ChatGLM2-6b show that the authors’ proposed CoE prompting consistently outperforms other typical promptings across all data sets.

This paper proposes CoE prompting to solve MDS tasks by the LLMs. CoE prompting can not only identify the key events but also ensure the conciseness of the summary. By this method, users can access the most relevant and important information quickly, improving their decision-making processes.

Developing a reliable cost estimate at the early stage of construction projects is challenging due to inadequate project information. Most of the information during this stage is qualitative, posing additional challenges to achieving accurate cost estimates. Additionally, there is a lack of tools that use qualitative project information and forecast the budgets required for project completion. This research, therefore, aims to develop a model for setting project budgets (excluding land) during the pre-conceptual stage of residential buildings, where project information is mainly qualitative.

Due to the qualitative nature of project information at the pre-conception stage, a natural language processing model, DistilBERT (Distilled Bidirectional Encoder Representations from Transformers), was trained to predict the cost range of residential buildings at the pre-conception stage. The training and evaluation data included 63,899 building permit activity records (2021–2022) from the Victorian State Building Authority, Australia. The input data comprised the project description of each record, which included project location and basic material types (floor, frame, roofing, and external wall).

This research designed a novel tool for predicting the project budget based on preliminary project information. The model achieved 79% accuracy in classifying residential buildings into three cost_classes ($100,000-$300,000, $300,000-$500,000, $500,000-$1,200,000) and F1-scores of 0.85, 0.73, and 0.74, respectively. Additionally, the results show that the model learnt the contextual relationship between qualitative data like project location and cost.

The current model was developed using data from Victoria state in Australia; hence, it would not return relevant outcomes for other contexts. However, future studies can adopt the methods to develop similar models for their context.

This research is the first to leverage a deep learning model, DistilBERT, for cost estimation at the pre-conception stage using basic project information like location and material types. Therefore, the model would contribute to overcoming data limitations for cost estimation at the pre-conception stage. Residential building stakeholders, like clients, designers, and estimators, can use the model to forecast the project budget at the pre-conception stage to facilitate decision-making.

This study investigates the integration of Industry 4.0 (I4.0) technologies with condition-based maintenance (CBM) in upstream oil and gas (O&G) operations, focussing on developing countries like Nigeria. The research identifies barriers to this integration and suggests solutions, intending to provide practical insights for improving operational efficiency in the O&G sector.

The study commenced with an exhaustive review of extant literature to identify existing barriers to I4.0 implementation and contextualise the study. Subsequent to this foundational step, primary data are gathered through the administration of carefully constructed questionnaires targeted at professionals specialised in maintenance within the upstream O&G sector. A semi-structured interview was also conducted to elicit more nuanced, contextual insights from these professionals. Analytically, the collected data were subjected to descriptive statistical methods for summarisation and interpretation with a measurement model to define the relationships between observed variables and latent construct. Moreover, the Relative Importance Index was utilised to systematically prioritise and rank the key barriers to I4.0 integration to CBM within the upstream O&G upstream sector.

The most ranked obstacles in integrating I4.0 technologies to the CBM strategy in the O&G industry are lack of budget and finance, limited engineering and technological resources, lack of support from executives and leaders of the organisations and lack of competence. Even though the journey of digitalisation has commenced in the O&G industry, there are limited studies in this area.

The study serves as both an academic cornerstone and a practical guide for the operational integration of I4.0 technologies within Nigeria's O&G upstream sector. Specifically, it provides an exhaustive analysis of the obstacles impeding effective incorporation into CBM practices. Additionally, the study contributes actionable insights for industry stakeholders to enhance overall performance and achieve key performance indices (KPIs).

This study aims to explore the dissemination and evolutionary path of online public opinion from a crisis management perspective. By clarifying the influencing factors and dynamic mechanisms of online public opinion dissemination, this study provides insights into attenuating the negative impact of online public opinion and creating a favorable ecological space for online public opinion.

This research employs bibliometric analysis and CiteSpace software to analyze 302 Chinese articles published from 2006 to 2023 in the China National Knowledge Infrastructure (CNKI) database and 276 English articles published from 1994 to 2023 in the Web of Science core set database. Through literature keyword clustering, co-citation analysis and burst terms analysis, this paper summarizes the core scientific research institutions, scholars, hot topics and evolutionary paths of online public opinion crisis management research from both Chinese and international academic communities.

The results show that the study of online public opinion crisis management in China and internationally is centered on the life cycle theory, which integrates knowledge from information, computer and system sciences. Although there are differences in political interaction and stage evolution, the overall evolutionary path is similar, and it develops dynamically in the “benign conflict” between the expansion of the research perspective and the gradual refinement of research granularity.

This study summarizes the research results of online public opinion crisis management from China and the international academic community and identifies current research hotspots and theoretical evolution paths. Future research can focus on deepening the basic theories of public opinion crisis management under the influence of frontier technologies, exploring the subjectivity and emotionality of web users using fine algorithms and promoting the international development of network public opinion crisis management theory through transnational comparison and international cooperation.

Since the introduction of the outstanding web AI chat system, ChatGPT, it has caused a significant impact in both academia and the business world. Many studies have started to explore its potential applications in various fields. However, there is a lack of research from the perspective of user experience. To fill this theoretical gap and provide a theoretical basis for the operation and design of related services, this study plans to develop a set of evaluation scales for AI chat system user experience and explore the relationship between various factors and user satisfaction.

This study obtained 41 evaluation indicators through literature review and user research. Subsequently, these indicators were used as questionnaire items, combined with satisfaction metrics. A total of 515 questionnaires were distributed, and factor analysis and linear regression were employed to determine the specific elements influencing user experience and the user satisfaction model.

This study found that the factors influencing user experience are usefulness, accuracy, logical inference, interactivity, growth, anthropomorphism, convenience, credibility, ease of use, creativity, and security. Among these factors, only accuracy, anthropomorphism, creativity, and security indirectly influence satisfaction through usefulness, while the rest of the factors have a direct positive impact on user satisfaction.

This study provides constructive suggestions for the design and operation of related services and serves as a reference for future theoretical research in this area.

Although numerous signal modalities are available for emotion recognition, audio and visual modalities are the most common and predominant forms for human beings to express their emotional states in daily communication. Therefore, how to achieve automatic and accurate audiovisual emotion recognition is significantly important for developing engaging and empathetic human–computer interaction environment. However, two major challenges exist in the field of audiovisual emotion recognition: (1) how to effectively capture representations of each single modality and eliminate redundant features and (2) how to efficiently integrate information from these two modalities to generate discriminative representations.

A novel key-frame extraction-based attention fusion network (KE-AFN) is proposed for audiovisual emotion recognition. KE-AFN attempts to integrate key-frame extraction with multimodal interaction and fusion to enhance audiovisual representations and reduce redundant computation, filling the research gaps of existing approaches. Specifically, the local maximum–based content analysis is designed to extract key-frames from videos for the purpose of eliminating data redundancy. Two modules, including “Multi-head Attention-based Intra-modality Interaction Module” and “Multi-head Attention-based Cross-modality Interaction Module”, are proposed to mine and capture intra- and cross-modality interactions for further reducing data redundancy and producing more powerful multimodal representations.

Extensive experiments on two benchmark datasets (i.e. RAVDESS and CMU-MOSEI) demonstrate the effectiveness and rationality of KE-AFN. Specifically, (1) KE-AFN is superior to state-of-the-art baselines for audiovisual emotion recognition. (2) Exploring the supplementary and complementary information of different modalities can provide more emotional clues for better emotion recognition. (3) The proposed key-frame extraction strategy can enhance the performance by more than 2.79 per cent on accuracy. (4) Both exploring intra- and cross-modality interactions and employing attention-based audiovisual fusion can lead to better prediction performance.

The proposed KE-AFN can support the development of engaging and empathetic human–computer interaction environment.

Technological advancement has forced academic libraries to change their traditional services and routines by adopting emerging technologies to respond to the changing information needs of their users who are now more technologically inclined and prefer to access information remotely and in a timely manner. Smart technologies are the recent trends in academic libraries. This research aims to investigate the level of smart information service implementation at academic libraries in Jordan. It also aimed to investigate the correlation between the level of smart information services offered by the libraries and the level of digital competencies among the library staff.

This research is designed using survey design to collect comprehensive information from the study participants. A questionnaire was disseminated to 340 respondents, and 246 questionnaires were returned and were suitable for analysis with a response rate of 72.4%.

The results indicated a moderate level of smart information service offered by academic libraries, as well as a moderate level of digital skills associated with the advocacy of smart information services. The results also indicated a strong and positive relationship between the level of smart information services at the investigated libraries and the level of digital competencies among the librarians.

The findings will help other academic libraries understand how to respond to the emergent change in users’ information-seeking behavior by understanding their available human resources competencies and the requirement to undergo this emergent change.

This paper provides insights and practical solutions for academic libraries in response to global information trends based on users’ behaviors. This research was conducted in Jordan as one of the developing countries and hence it provides insights of the situation there. It will help academic libraries in Jordan and the region to handle and cope with the challenges associated with technology acceptance based on its staff level of digital competencies. The contribution of this research that it was done in a developing country where progress in the filed can be considered slow because of many factors, mainly economics, where institutions focus on essential library objectives, which are information resources development and databases subscriptions.

This study offers an in-depth examination of Google Bard, an advanced artificial intelligence chatbot created by Google, focusing specifically on its potential impact on academic research. This discussion aims to comprehensively explore the features of Google Bard, highlighting its capabilities in data management, facilitating collaborative discussions, and enhancing accessibility to complex research. In addition to the aforementioned positive characteristics, we will also delve into the limitations and ethical considerations associated with this innovative device. The functionality of the system is constrained by the limitations imposed by its pre-established algorithms and training data. In addition, there are significant concerns regarding data privacy, potential biases in its responses stemming from its training data, and the wider societal implications associated with a heavy reliance on machine-generated content. Ensuring responsible and ethical utilization of Bard necessitates Google's provision of transparent communication regarding its development process. In light of the prominent functionalities demonstrated by Google Bard, it is imperative for researchers to engage in a rigorous examination of the information it presents, thereby safeguarding against the inadvertent propagation of misinformation or biased viewpoints. This will lay the groundwork for its effective integration into the academic research methodology.

This study aims to emphasize the integration of lean start-up and design thinking approaches and investigate how they may be used together.

The report uses a systematic literature review methodology to analyze and summarize previous research on combining lean start-up and design thinking. Inferences were discovered and analyzed after relevant publications were chosen based on predetermined inclusion criteria.

The research shows that combining lean start-up and design thinking significantly impacts entrepreneurship. Start-ups can efficiently uncover consumer needs, reduce risks and improve their product or service offerings by combining the client-centricity of design thinking with the iterative and data-driven concepts of lean start-up. This integration promotes an innovative culture, gives teams the freedom to try new things and learn from mistakes and raises the possibility of start-up success.

The dependence on pre-existing literature, which might cover only some potential uses and circumstances, is a weakness of this research. It is advised that more empirical research be conducted to determine the precise circumstances in which the integrated strategy performs best. Future studies should also explore the difficulties and drawbacks of using these approaches to offer suggestions for overcoming them and maximizing their advantages.

The findings have significant ramifications for business owners and other professionals working in the start-up environment. The combination of lean start-up and design thinking emphasizes the relevance of early customer interaction and empathy-driven design. To foster creativity and hasten the expansion of start-ups, practitioners are urged to create a comprehensive strategy that integrates the advantages of both techniques. Through this integration, business owners may develop solutions that appeal to their target market, increasing adoption rates and market competitiveness.

This study is interesting in comparing lean start-up and design thinking, emphasizing the overlaps and benefits of their application to entrepreneurship. This study discusses successful start-up methods by offering suggestions for future research and practice. It also provides a basis for further developing and adopting the integrated approach.

Nurse leaders are challenged by ethical issues in today’s complex health-care settings. The purpose of this study was to describe and analyze key elements of moral distress identified by nurse leaders from health-care systems in the USA, Germany, Austria and Switzerland. The aim was to develop an understanding of distressing ethical issues nurse leaders face in the USA and three German-speaking European countries.

This descriptive cross-sectional study surveyed a convenience sample of nurse leaders in the USA, Germany, Austria and Switzerland. The voluntary, anonymous survey also included qualitative questions and was distributed using the Qualtrics® platform. A thematic analysis of the qualitative data in each country was carried out and a comparative analysis identified similarities and differences between the groups of nurse leaders comparing the US data to that from three German-speaking European countries.

The survey was completed by 316 nurse leaders: Germany, Austria, and Switzerland (n = 225) and the USA (n = 91). Similar themes identified as causing all nurse leaders moral distress included a lack of individual and organizational integrity, hierarchical and interprofessional issues, lack of nursing professionalism, patient care/patient safety concerns, finances negatively impacting care and issues around social justice. Within these six themes, there were also differences between the USA and the three German-speaking European countries.

Understanding the experiences associated with distressing ethical situations can allow nurse leaders and organizations to focus on solutions and develop resilience to reduce moral distress in the USA and three German-speaking European countries.