Search results

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.

This study aims to develop an empathetic and user-centric customer support service design model. Though service design has been a critical research focus for several decades, few studies focus on customer support services. As customer support gains importance as a source of competitive advantage in the present era, this paper aims to contribute to industry and academia by exploring the service design model.

The study adopted a theories-in-use approach to elucidate mental models based on the industry’s best practices. In-depth interviews with 62 professionals led to critical insights into customer service design development, supported by service-dominant logic and theory of mind principles.

The ensuing insights led to a model that connects the antecedents and outcomes of empathetic and user-centric customer service design. The precursors include people, processes and technology, while the results are user experience, service trust and service advocacy. The model also emphasises the significance of the user’s journey and the user service review in the overall service design.

The model developed through this study addresses the critical gap concerning the lack of service design research in customer support services. The key insights from this study contribute to the ongoing research endeavours towards transitioning customer support services from an operational unit to a strategic value-creating function. Future scholars may investigate the applicability of the empathetic user service design across cultures and industries. The new model must be customised using real-time data and analytics across user journey stages.

The empathetic and user-centric design can elevate the customer service function as a significant contributor to the overall customer experience, loyalty and positive word of mouth. Practitioners can adopt the new model to provide superior customer service experiences. This original research was developed through crucial insights from interviews with senior industry professionals.

This research is the original work developed through the key insights from the interview with senior industry professionals.

Video game streaming (VGS) is emerging as an extremely popular, highly interactive, inordinately subscribed and very dynamic form of digital media. Incorporated environmental elements, gratifications and user pre-existing attitudes in VGS, this paper presents the development of an extended model of uses and gratification theory (EUGT) for predicting users' behavior in novel technological context.

The proposed model was empirically tested in VGS context due to its popularity, interactivity and relevance. Data collected from 308 VGS users and structural equation modeling (SEM) was employed to assess the hypotheses. Multi-model comparison technique was used to assess the explanatory power of EUGT.

The findings confirmed three significant types elements in determining VGS viewers' engagement, including gratifications (e.g. involvement), environmental cues (e.g. medium appeal) and user predispositions (e.g. pre-existing attitudes). The results revealed that emerging technologies provide potential opportunities for new motives and gratifications, and highlighted the significant of pre-existing attitudes as a mediator in the gratification-uses link.

This study is one of its kind in tackling the criticism on UGT of considering media users too rational or active. The study achieved this objective by considering environmental impacts on user behavior which is largely ignored in recent UGT studies. Also, by incorporating users pre-existing attitudes into UGT framework, this study conceptualized and empirically verified the higher explanatory power of EUGT through a novel multi-modal approach in VGS. Compared to other rival models, EUGS provides a more robust explanation of users' behavior. The findings contribute to the literature of UGT, VGS and users' engagement.

Digital Libraries are complex, and this complexity is a motive to study user success on the behalf of appropriate user success models. These models comprise the factors which play a part between people, technology and organizations. The purpose of this study was to specify and examine an integrated digital library user success (IDLUS) model within the context of digital library settings, Higher Education Commission National Digital Library (HEC-NDL) of Pakistan, by adopting and reusing the existing digital library and Web success models.

Stratified random sampling technique was used to choose the sample from the University of the Punjab, a highly ranked public sector university in Pakistan. Participants were asked to complete an adapted survey questionnaire. A total of 355 completed and usable questionnaires were obtained. Data analyses through confirmatory factor analyses and structural equation modeling produced the results that have supported the proposed IDLUS model. The proposed IDLUS model was tested and supported through model fit statistics in the academic computing environment of the HEC-NDL of Pakistan.

Findings revealed that relationships between the latent variables hypothesized in the model were confirmed.

The study has both theoretical and practical ramifications for academicians and information system designers and developers.

The IDLUS model is recommended first time in the history of librarianship in Pakistan as an overall user success model in the digital library information system computing environment. That made numerous recommendations for future research in the field of information management, particularly for digital library development at national and international levels.

User feedback inferred from the user's search-time behavior could improve the learning to rank (L2R) algorithms. Click models (CMs) present probabilistic frameworks for describing and predicting the user's clicks during search sessions. Most of these CMs are based on common assumptions such as Attractiveness, Examination and User Satisfaction. CMs usually consider the Attractiveness and Examination as pre- and post-estimators of the actual relevance. They also assume that User Satisfaction is a function of the actual relevance. This paper extends the authors' previous work by building a reinforcement learning (RL) model to predict the relevance. The Attractiveness, Examination and User Satisfaction are estimated using a limited number of the features of the utilized benchmark data set and then they are incorporated in the construction of an RL agent. The proposed RL model learns to predict the relevance label of documents with respect to a given query more effectively than the baseline RL models for those data sets.

In this paper, User Satisfaction is used as an indication of the relevance level of a query to a document. User Satisfaction itself is estimated through Attractiveness and Examination, and in turn, Attractiveness and Examination are calculated by the random forest algorithm. In this process, only a small subset of top information retrieval (IR) features are used, which are selected based on their mean average precision and normalized discounted cumulative gain values. Based on the authors' observations, the multiplication of the Attractiveness and Examination values of a given query–document pair closely approximates the User Satisfaction and hence the relevance level. Besides, an RL model is designed in such a way that the current state of the RL agent is determined by discretization of the estimated Attractiveness and Examination values. In this way, each query–document pair would be mapped into a specific state based on its Attractiveness and Examination values. Then, based on the reward function, the RL agent would try to choose an action (relevance label) which maximizes the received reward in its current state. Using temporal difference (TD) learning algorithms, such as Q-learning and SARSA, the learning agent gradually learns to identify an appropriate relevance label in each state. The reward that is used in the RL agent is proportional to the difference between the User Satisfaction and the selected action.

Experimental results on MSLR-WEB10K and WCL2R benchmark data sets demonstrate that the proposed algorithm, named as SeaRank, outperforms baseline algorithms. Improvement is more noticeable in top-ranked results, which usually receive more attention from users.

This research provides a mapping from IR features to the CM features and thereafter utilizes these newly generated features to build an RL model. This RL model is proposed with the definition of the states, actions and reward function. By applying TD learning algorithms, such as the Q-learning and SARSA, within several learning episodes, the RL agent would be able to learn how to choose the most appropriate relevance label for a given pair of query–document.

With the emergence of digital twins, the construction industry is looking toward improving the inspection and maintenance of all kinds of assets, such as bridges, roads and utilities. The purpose of this paper is to provide insights into how the development of an interactive digital twin creates a variety of interactions between users of this technology and assets to be monitored.

The development of a digital twin inspection model, focusing on the specific case of a sewage pumping station, is chosen as the subject of a case study. Through the development of this model, this study explores the various user–technology interactions that can be designed in a digital twin context.

Users interact with digital twins by following virtual instructions in a certain way, which creates a “quasi-other” relationship. A digital twin based on virtual reality (VR) also make users feel as if they are within the created VR of an inspection site, thereby immersing them in the VR environment. The design of a VR-based digital twin, which is determined by decisions made during the development process, shapes the context in which users interact with the technology and assets.

This study shows that a digital twin in construction practice may play different “actant” roles having different types of influences. Analyzing these actant roles and influences in terms of force and visibility adds a new perspective on the interaction between users and digital twins in construction and asset monitoring practice.

Companies are increasingly implementing business process management systems (BPMSs) to support their processes. However, there is a gap in the literature regarding whether users also use BPMSs to manage the knowledge needed for processes to be completed. This study aims to analyze the factors that cause users to use BPMSs to manage the knowledge required in business processes.

The paper proposes an original model that integrates two successful information system models applied to BPMSs and knowledge management systems. To test the hypotheses derived from this new model, data were collected from 242 mature BPMS users from 12 Spanish and Latin American companies. Structural equation modeling with AMOS was used to examine the model.

Users’ perceived usefulness of a BPMS when using it for knowledge management (KM) is the only factor influencing them to use it for KM.

This study has practical implications for managers wishing to successfully implement a BPMS to support processes and for employees to use the knowledge embedded in the tool. The latter will only happen if users perceive the tool’s usefulness for KM.

To the best of the authors’ knowledge, this model is the first empirically validated model to successfully analyze BPMS users’ tendency to use BPMSs as a tool to support necessary KM in processes.

This paper aims to propose a user adoption model of human resource information system (HRIS) in the Jordanian public sector by integrating the task technology fit (TTF) model and the unified theory of acceptance and usage of technology (UTAUT).

Using a quantitative approach, survey data were collected using an online survey from employees working in four different public organizations in Jordan, and structural equation modelling has been used to validate the research model.

The study found that among the constructs of the UTAUT model performance expectancy, social influence and facilitating condition have a significant effect on users’ behavioural intention to adopt HRIS. Furthermore, the results also reveal that effort expectancy has an insignificant effect on adoption behaviour. The findings also show that all TTF hypotheses were supported by the data collected. Both task characteristics and technology characteristics have a significant effect on the TTF construct, which further determines users’ adoption behaviour.

These findings contribute to the extant academic literature and have practical implications, improving the understanding of the HRIS adoption and use in public sector organizations.

The purpose of this study is to investigate how book group recommendations can be used as a meaningful way to suggest suitable books to users, given the increasing number of individuals engaging in sharing and discussing books on the web.

The authors propose reviews fine-grained classification (CFGC) and its related models such as CFGC1 for book group recommendation. These models can categorize reviews successively by function and role. Constructing the BERT-BiLSTM model to classify the reviews by function. The frequency characteristics of the reviews are mined by word frequency analysis, and the relationship between reviews and total book score is mined by correlation analysis. Then, the reviews are classified into three roles: celebrity, general and passerby. Finally, the authors can form user groups, mine group features and combine group features with book fine-grained ratings to make book group recommendations.

Overall, the best recommendations are made by Synopsis comments, with the accuracy, recall, F-value and Hellinger distance of 52.9%, 60.0%, 56.3% and 0.163, respectively. The F1 index of the recommendations based on the author and the writing comments is improved by 2.5% and 0.4%, respectively, compared to the Synopsis comments.

Previous studies on book recommendation often recommend relevant books for users by mining the similarity between books, so the set of book recommendations recommended to users, especially to groups, always focuses on the few types. The proposed method can effectively ensure the diversity of recommendations by mining users’ tendency to different review attributes of books and recommending books for the groups. In addition, this study also investigates which types of reviews should be used to make book recommendations when targeting groups with specific tendencies.

The purpose of this study is to understand user perceptions and misconceptions regarding security tools. Security and privacy-preserving tools (for brevity, the authors term them as “security tools” in this paper, unless otherwise specified) are designed to protect the security and privacy of people in the digital environment. However, inappropriate use of these tools can lead to unexpected consequences that are preventable. Hence, it is significant to examine why users do not understand the security tools.

The authors conducted a qualitative study with 40 participants in the USA to investigate the prevalent misconceptions of people regarding security tools, their perceptions of data access and the corresponding impact on their usage behavior and data protection strategies.

While security vulnerabilities are often rooted in people’s internet usage behavior, this study examined user’s mental models of the internet and unpacked how the misconceptions about security tools relate to those mental models.

Based on the findings, this study offers recommendations highlighting the design aspects of security tools that need careful attention from researchers and industry practitioners, to alleviate users’ misconceptions and provide them with accurate conceptual models toward the desired use of security tools.