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.

In the COVID-19 era, sign language (SL) translation has gained attention in online learning, which evaluates the physical gestures of each student and bridges the communication gap between dysphonia and hearing people. The purpose of this paper is to devote the alignment between SL sequence and nature language sequence with high translation performance.

SL can be characterized as joint/bone location information in two-dimensional space over time, forming skeleton sequences. To encode joint, bone and their motion information, we propose a multistream hierarchy network (MHN) along with a vocab prediction network (VPN) and a joint network (JN) with the recurrent neural network transducer. The JN is used to concatenate the sequences encoded by the MHN and VPN and learn their sequence alignments.

We verify the effectiveness of the proposed approach and provide experimental results on three large-scale datasets, which show that translation accuracy is 94.96, 54.52, and 92.88 per cent, and the inference time is 18 and 1.7 times faster than listen-attend-spell network (LAS) and visual hierarchy to lexical sequence network (H2SNet) , respectively.

In this paper, we propose a novel framework that can fuse multimodal input (i.e. joint, bone and their motion stream) and align input streams with nature language. Moreover, the provided framework is improved by the different properties of MHN, VPN and JN. Experimental results on the three datasets demonstrate that our approaches outperform the state-of-the-art methods in terms of translation accuracy and speed.

This study aims to identify specific factors that facilitate engagement and stay intention among Generation Z employees in the Indian banking, financial services and insurance (BFSI) context. Furthermore, using the frequency distribution of the identified factors, this study has ranked them in order of their association with stay intention.

Data were collected from 22 Gen Z employees working in the Indian private BFSI sector using unstructured interviews. Inductive content analysis was applied to identify the factors improving engagement and stay intention. Moreover, quantitative content analysis was applied to calculate the frequency distribution of the identified factors.

The study identified six prominent factors, namely, transformational leadership, employee investment practices, egalitarian practices, work-life balance, job crafting and sustainability, which significantly enhance employee engagement and stay intention among Gen Z employees. Moreover, based on the results of quantitative content analysis, it was found that transformational leadership exhibited the highest frequency in association with employee engagement and stay intention. Following this were employee involvement, egalitarian practices, work-life balance, job crafting and sustainability.

In the coming days, Generation Z will contribute to almost one-third of India’s workforce, of which the BFSI sector will be the major employer. However, the issue with this generation is their retention. Hence, the study identifies factors ensuring engagement and stay intention.

Owing to the paucity of research on stay intention as a variable of interest, this study tries to capture the perceptions of Gen Z towards factors inducing their engagement and stay intention. This study assesses intention to stay (ITS) as compared to intention to leave (ITL) as it is a proactive indicator of turnover. Lastly, this study uses a qualitative approach to identify factors influencing stay intention and engagement based on interactions with employees, which, to the best of the authors’ knowledge, no prior study has attempted.

Applying traditional grounded theory techniques, the present research reanalyzed secondary data from four previously conducted studies to explore how generativity is manifested in young adults.

A new conceptual model of generativity was developed to depict how generativity manifests among this age group.

This study's findings provide leadership educators with a refined approach to interacting with this construct while simultaneously increasing young adults’ potential ability to experience the benefits available to them through generativity at an earlier stage in their lives.

This study advances the field of leadership education by establishing foundational insight into the uniqueness of generativity’s development in young adulthood.

This study aims to examine the dynamics of traditional wayang kulit or shadow puppet knowledge management in a community-based enterprise (CBE) known as “Wisata Wayang” in Wukirsari Village, Yogyakarta, Indonesia.

A qualitative case study was adopted, which allows the author to explore the dynamics or uniqueness of an event or cultural phenomenon more deeply.

The shadow puppet is an artefact of Javanese culture with rich life philosophy and wisdom. It guides people the pursuit of harmony with themselves, others, the universe and God. The success of knowledge management of the shadow puppet at CBE was supported by the high entrepreneurial orientation of the administrators. This study showed that entrepreneurial orientation should be extended into sociopreneurial with additional aspects, including preservation mission and communality, promoting the emergence of grassroots innovations. The knowledge of shadow puppet craft in this village is passed through nyantrik, also known as apprenticeship.

No previous research has explored the dynamics of traditional knowledge management in the context of CBE in Indonesia. As Indonesia has rich traditional knowledge from hundreds of tribes and prominent communal cultures, this study of community-based knowledge management contributes new insights in the knowledge management literature.

This study aims to address the existing knowledge gap by investigating teachers’ adoption of ChatGPT for educational purposes. The study specifically focuses on identifying the factors that motivate and inhibit teachers in adoption of ChatGPT in higher education institutions (HEIs).

This research has used interpretative phenomenological analysis – a qualitative approach. Through in-depth interviews among the teachers, data was collected to identify the motivating and inhibiting factors that impacted teachers’ willingness to adopt ChatGPT. The data was collected from 48 teachers working across HEIs of Uttarakhand region in India.

The analysis revealed seven themes under motivating factors that encourage teachers to adopt ChatGPT for their educational purposes. These include time factor, tool for competitive edge, learning enhancement tool for students, research facilitator, benefits in educational settings, troubleshooter and easy to use. On the other hand, inhibiting factors comprise five themes, which include technical difficulties, limited features for educational and research purposes, tool for handicapping innovation and creativity, lack of personal touch and ethical considerations.

The findings will be valuable for HEIs in establishing policies that promote the appropriate and effective use of ChatGPT. Moreover, the study provides recommendations to ChatGPT solution providers for improving ChatGPT services for effective adoption of ChatGPT among teachers and implementation at HEIs. Further, it contributes to the body of literature by filling a knowledge gap about teacher adoption of ChatGPT in the HEIs. Through qualitative research, the study has pinpointed specific motivating and inhibiting factors that affect teacher adoption of ChatGPT.

Unlike previous studies that primarily explored the potential advantages and drawbacks of ChatGPT in education, this research study delves deeper into the topic. It makes a substantial contribution to our understanding of ChatGPT adoption among teachers by identifying distinct factors that either motivate or inhibit teachers from adopting ChatGPT for job related purposes. The study provides novel insights that were previously mislaid, thereby introducing a fresh perspective to the existing literature

This study aims to construct a sentiment series generation method for danmu comments based on deep learning, and explore the features of sentiment series after clustering.

This study consisted of two main parts: danmu comment sentiment series generation and clustering. In the first part, the authors proposed a sentiment classification model based on BERT fine-tuning to quantify danmu comment sentiment polarity. To smooth the sentiment series, they used methods, such as comprehensive weights. In the second part, the shaped-based distance (SBD)-K-shape method was used to cluster the actual collected data.

The filtered sentiment series or curves of the microfilms on the Bilibili website could be divided into four major categories. There is an apparently stable time interval for the first three types of sentiment curves, while the fourth type of sentiment curve shows a clear trend of fluctuation in general. In addition, it was found that “disputed points” or “highlights” are likely to appear at the beginning and the climax of films, resulting in significant changes in the sentiment curves. The clustering results show a significant difference in user participation, with the second type prevailing over others.

Their sentiment classification model based on BERT fine-tuning outperformed the traditional sentiment lexicon method, which provides a reference for using deep learning as well as transfer learning for danmu comment sentiment analysis. The BERT fine-tuning–SBD-K-shape algorithm can weaken the effect of non-regular noise and temporal phase shift of danmu text.

The present study distinguishes itself by pioneering an innovative framework that integrates key elements of prospect theory and the fundamental principles of electronic word of mouth (EWOM) to forecast Bitcoin/USD price fluctuations using Twitter sentiment analysis.

We utilized Twitter data as our primary data source. We meticulously collected a dataset consisting of over 3 million tweets spanning a nine-year period, from 2013 to 2022, covering a total of 3,215 days with an average daily tweet count of 1,000. The tweets were identified by utilizing the “bitcoin” and/or “btc” keywords through the snscrape python library. Diverging from conventional approaches, we introduce four distinct variables, encompassing normalized positive and negative sentiment scores as well as sentiment variance. These refinements markedly enhance sentiment analysis within the sphere of financial risk management.

Our findings highlight the substantial impact of negative sentiments in driving Bitcoin price declines, in contrast to the role of positive sentiments in facilitating price upswings. These results underscore the critical importance of continuous, real-time monitoring of negative sentiment shifts within the cryptocurrency market.

Our study holds substantial significance for both risk managers and investors, providing a crucial tool for well-informed decision-making in the cryptocurrency market. The implications drawn from our study hold notable relevance for financial risk management.

We present an innovative framework combining prospect theory and core principles of EWOM to predict Bitcoin price fluctuations through analysis of Twitter sentiment. Unlike conventional methods, we incorporate distinct positive and negative sentiment scores instead of relying solely on a single compound score. Notably, our pioneering sentiment analysis framework dissects sentiment into separate positive and negative components, advancing our comprehension of market sentiment dynamics. Furthermore, it equips financial institutions and investors with a more detailed and actionable insight into the risks associated not only with Bitcoin but also with other assets influenced by sentiment-driven market dynamics.

Given the critical role of user-generated content (UGC) in e-commerce, exploring various aspects of UGC can aid in understanding user purchase intention and commodity recommendation. Therefore, this study investigates the impact of UGC on purchase decisions and proposes new recommendation models based on sentiment analysis, which are verified in Douban, one of the most popular UGC websites in China.

After verifying the relationship between various factors and product sales, this study proposes two models, collaborative filtering recommendation model based on sentiment (SCF) and hidden factors topics recommendation model based on sentiment (SHFT), by combining traditional collaborative filtering model (CF) and hidden factors topics model (HFT) with sentiment analysis.

The results indicate that sentiment significantly influences purchase intention. Furthermore, the proposed sentiment-based recommendation models outperform traditional CF and HFT in terms of mean absolute error (MAE) and root mean square error (RMSE). Moreover, the two models yield different outcomes for various product categories, providing actionable insights for organizers to implement more precise recommendation strategies.

The findings of this study advocate the incorporation of UGC sentimental factors into websites to heighten recommendation accuracy. Additionally, different recommendation strategies can be employed for different products types.

This study introduces a novel perspective to the recommendation algorithm field. It not only validates the impact of UGC sentiment on purchase intention but also evaluates the proposed models with real-world data. The study provides valuable insights for managerial decision-making aimed at enhancing recommendation systems.