Search results

The purpose of this paper is to propose a mobile and social-based question-and-answer (Q&A) system that analyzes users' social relationships and past answering behavior, considers users' interest similarity and answer quality to infer suitable respondents and forwards the questions to users that are willing to give high quality answers.

This research applies first-order logic (FOL) inference calculation to generate question/interest ID that combines a users' social information, interests and social network intimacy to choose the nodes that can provide high-quality answers. After receiving a question, a friend can answer it, forward it to their friends according to the number of TTL (Time-to-Live) hops, or send the answer directly to the server. This research collected data from the TripAdvisor.com website and uses it for the experiment. The authors also collected previously answered questions from TripAdvisor.com; thus, subsequent answers could be forwarded to a centralized server to improve the overall performance.

The authors have first noticed that even though the proposed system is decentralized, it can still accurately identify the appropriate respondents to provide high-quality answers. In addition, since this system can easily identify the best answerers, there is no need to implement broadcasting, thus reducing the overall execution time and network bandwidth required. Moreover, this system allows users to accurately and quickly obtain high-quality answers after comparing and calculating interest IDs. The system also encourages frequent communication and interaction among users. Lastly, the experiments demonstrate that this system achieves high accuracy, high recall rate, low overhead, low forwarding cost and low response rate in all scenarios.

This paper proposes a mobile and social-based Q&A system that applies FOL inference calculation to analyze users' social relationships and past answering behavior, considers users' interest similarity and answer quality to infer suitable respondents and forwards the questions to users that are willing to give high quality answers. The experiments demonstrate that this system achieves high accuracy, high recall rate, low overhead, low forwarding cost and low response rate in all scenarios.

The collaborative filtering algorithm is a classical and widely used approach in product recommendation systems. However, the existing algorithms rely mostly on common ratings of items and do not consider temporal information about items or user interests. To solve this problem, this study proposes a new user-item composite filtering (UICF) recommendation framework by leveraging temporal semantics.

The UICF framework fully utilizes the time information of item ratings for measuring the similarity of items and takes into account the short-term and long-term interest decay for computing users’ latest interest degrees. For an item to be probably recommended to a user, the interest degrees of the user on all the historically rated items are weighted by their similarities with the item to be recommended and then added up to predict the recommendation degree.

Comprehensive experiments on the MovieLens and KuaiRec datasets for user movie recommendation were conducted to evaluate the performance of the proposed UICF framework. Experimental results show that the UICF outperformed three well-known recommendation algorithms Item-Based Collaborative Filtering (IBCF), User-Based Collaborative Filtering (UBCF) and User-Popularity Composite Filtering (UPCF) in the root mean square error (RMSE), mean absolute error (MAE) and F1 metrics, especially yielding an average decrease of 11.9% in MAE.

A UICF recommendation framework is proposed that combines a time-aware item similarity model and a time-wise user interest degree model. It overcomes the limitations of common rating items and utilizes temporal information in item ratings and user interests effectively, resulting in more accurate and personalized recommendations.

Prior research on user-generated content (UGC) contributions has primarily focused on self-centered or other-centered motives, paying limited attention to the concept of enlightened self-interest, in which both motives coexist in a single organism. Additionally, the factors influencing enlightened self-interest and their effects in different circumstances are yet to be explored. Drawing on theoretical lenses rooted in the switching barriers perspective and stimulus–organism–response framework, this study posits that dedication-based switching barriers (community–member relationship quality, member–member relationship quality, and content attractiveness) positively relate to enlightened self-interest, whereas constraint-based switching barriers (switching costs) moderate the relationship between dedication-based switching barriers and enlightened self-interest in social media communities (SMCs). Members' enlightened self-interest in turn influences both the creation and co-creation of UGC.

This study comprised two quantitative studies: an online survey-based study (Study 1) and an online scenario-based experiment (Study 2). Study 1 surveyed 613 respondents, while Study 2 included 749 participants. Both studies employed structural equation modeling and bootstrapping techniques for analysis.

The findings indicate that dedication-based switching barriers positively affect users' enlightened self-interest, which in turn is positively associated with UGC creation and co-creation. Switching costs moderate the relationship between relationship quality (community–member and member–member) and enlightened self-interest.

This study complements the current understanding of how the association between dedication- and constraint-based switching barriers and users' enlightened self-interests influence user-generated contributions.

The increasing popularity of music streaming services also increases the need to customize the services for each user to attract and retain customers. Most of the music streaming services will not have explicit ratings for songs; they will have only implicit feedback data, i.e user listening history. For efficient music recommendation, the preferences of the users have to be infered, which is a challenging task.

Preferences of the users can be identified from the users' listening history. In this paper, a hybrid music recommendation system is proposed that infers features from user's implicit feedback and uses the hybrid of content-based and collaborative filtering method to recommend songs. A Content Boosted K-Nearest Neighbours (CBKNN) filtering technique was proposed, which used the users' listening history, popularity of songs, song features, and songs of similar interested users for recommending songs. The song features are taken as content features. Song Frequency–Inverse Popularity Frequency (SF-IPF) metric is proposed to find the similarity among the neighbours in collaborative filtering. Million Song Dataset and Echo Nest Taste Profile Subset are used as data sets.

The proposed CBKNN technique with SF-IPF similarity measure to identify similar interest neighbours performs better than other machine learning techniques like linear regression, decision trees, random forest, support vector machines, XGboost and Adaboost. The performance of proposed SF-IPF was tested with other similarity metrics like Pearson and Cosine similarity measures, in which SF-IPF results in better performance.

This method was devised to infer the user preferences from the implicit feedback data and it is converted as rating preferences. The importance of adding content features with collaborative information is analysed in hybrid filtering. A new similarity metric SF-IPF is formulated to identify the similarity between the users in collaborative filtering.

As museums and other memory institutions continue to invest considerably in mass-digitising collections and participating in large search portals, it is essential to understand existing and potential users, their motivations and search needs to inform collections’ documentation. In this article, we discuss insights from a collaborative project with National Museums Scotland, set up to enhance the findability of collection images and inform documentation practices by understanding the collections users and their search terms.

The research involved interviews with National Museums Scotland staff, users and non-users of the Museums’ Search our Collections portal encompassing a concept mapping and card sort activity; online surveys and content analysis of user search queries.

The project revealed that participants are interested in searching the online collections by terms often not represented in collections metadata, including terms related to identity (their own but also others’) and social context (e.g. through seasonal and social events); emotional and sensory interests (e.g. visual characteristics) and narrative themes (e.g. on under-represented histories).

Based on the findings, we further theorise the semantic gap in online museum collection metadata. To bridge this gap and cater to how users search, we argue for a paradigm shift in documentation practices: suggesting practitioners should not only view collection images as information but also tap into their rich potential for enabling social and affective connections.

The study aims to investigate the characteristics of the current situation of library programs and explore the possible reasons behind the low participation in Hong Kong. It focuses on the development of library programs in the era of digital technology, which can lead to discussion and reflections on the further development of library programs with innovative technology services.

This study applied a mixed-method research approach to investigate the current situation of library programming and the reasons for low participation in Hong Kong. The first part analyzes the characteristics of library programs offered by the Hong Kong Public Libraries (HKPL) through data collection from the HKPL website. The second part of this study investigated the reasons behind the low participation in library programs through quantitative research through an online survey.

The findings show that current library programs were dominated by reading activities and children's programs to a great extent, which both users and non-users are not very interested in. Further, most respondents expressed more interest in cultural and leisure events and hands-on activities (especially new technologies related) than traditional library programming. Many lapsed and non-users chose not to attend the library programs for boredom and uselessness. As a result, there is a need for HKPL to adjust its services to stay relevant to the needs and interests of local communities.

Scant studies explored the reasons behind non-users of public library programs, especially in Asia. This research contributes to the literature by analyzing and proposing the characteristics of the current situation of library programs and exploring the possible reasons behind the low participation in Hong Kong.

With the increasing number of mobile applications, efficiently recommending mobile applications to users has become a challenging problem. Although existing mobile application recommendation approaches based on user attributes and behaviors have achieved notable effectiveness, they overlook the diffusion patterns and interdependencies of topic-specific mobile applications among user groups. mobile applications among user groups. This paper aims to capture the diffusion patterns and interdependencies of mobile applications among user groups. To achieve this, a topic-aware neural network-based mobile application recommendation method, referred to as TN-MR, is proposed.

In this method, first, the user representations are enhanced by introducing a topic-aware attention layer, which captures both the topic context and the diffusion history context. Second, it exploits a time-decay mechanism to simulate changes in user interest. Multitopic user representations are aggregated by the time decay module to output the user representations of cascading representations under multiple topics. Finally, user scores that are likely to download the mobile application are predicted and ranked.

Experimental comparisons and analyses were conducted on the actual 360App data set, and the results demonstrate that the effectiveness of mobile application recommendations can be significantly improved by using TN-MR.

In this paper, the authors propose a mobile application recommendation method based on topic-aware attention networks. By capturing the diffusion patterns and dependencies of mobile applications, it effectively assists users in selecting their applications of interest from thousands of options, significantly improving the accuracy of mobile application recommendations.

Predicting a user’s click-through rate on an advertisement or item often uses deep learning methods to mine hidden information in data features, which can provide users with more accurate personalized recommendations. However, existing works usually ignore the problem that the drift of user interests may lead to the generation of new features when they compute feature interactions. Based on this, this paper aims to design a model to address this issue.

First, the authors use graph neural networks to model users’ interest relationships, using the existing user features as the node features of the graph neural networks. Second, through the squeeze-and-excitation network mechanism, the user features and item features are subjected to squeeze operation and excitation operation, respectively, and the importance of the features is adaptively adjusted by learning the channel weights of the features. Finally, the feature space is divided into multiple subspaces to allocate features to different models, which can improve the performance of the model.

The authors conduct experiments on two real-world data sets, and the results show that the model can effectively improve the prediction accuracy of advertisement or item click events.

In the study, the authors propose graph network and feature squeeze-and-excitation model for click-through rate prediction, which is used to dynamically learn the importance of features. The results indicate the effectiveness of the model.

With the continuous increase of users, resources and tags, social tagging systems gradually present the characteristics of “big data” such as large number, fast growth, complexity and unreliable quality, which greatly increases the complexity of recommendation. The contradiction between the efficiency and effectiveness of recommendation service in social tagging is increasingly becoming prominent. The purpose of this study is to incorporate topic optimization into collaborative filtering to enhance both the effectiveness and the efficiency of personalized recommendations for social tagging.

Combining the idea of optimization before service, this paper presents an approach that incorporates topic optimization into collaborative recommendations for social tagging. In the proposed approach, the recommendation process is divided into two phases of offline topic optimization and online recommendation service to achieve high-quality and efficient personalized recommendation services. In the offline phase, the tags' topic model is constructed and then used to optimize the latent preference of users and the latent affiliation of resources on topics.

Experimental evaluation shows that the proposed approach improves both precision and recall of recommendations, as well as enhances the efficiency of online recommendations compared with the three baseline approaches. The proposed topic optimization–incorporated collaborative recommendation approach can achieve the improvement of both effectiveness and efficiency for the recommendation in social tagging.

With the support of the proposed approach, personalized recommendation in social tagging with high quality and efficiency can be achieved.

Running advertising campaigns and attracting the traffic, as well as collecting information from users who have entered the website once, provides the conditions to perform retargeting campaigns and consequently increases website visit rates and sales. The purpose of this research is to design a roadmap of retargeting campaign for small and medium enterprises (SMEs), as well as to compare normal and retargeting advertising campaigns in order to confirm the effectiveness of retargeting campaigns.

A single-case-study strategy was adopted by choosing advertising Company-X to design the roadmap of retargeting campaigns and evaluate its effectiveness. Using a purposive sampling, semi-structured interviews were conducted with 14 experts of advertising Company-X. Furthermore, the documents and reports available in the company were also analyzed. Thematic analysis was employed to analyze the interviews and documents. Next, a one-way ANOVA test and a two-sample t-test were used to measure the effectiveness of retargeting campaigns of the Company-X compared to normal campaigns with secondary data of 22 SMEs for a six-month period.

The qualitative phase led to the presentation of a roadmap for the retargeting campaigns in three stages: preparation, process and implementation. The results of the quantitative phase revealed that the ratio of clicks to impressions (click-through rate) and the ratio of successful purchase tags to clicks (conversion rate) are much higher in the retargeting product campaign. Therefore, the performance of selected SMEs as an example in the product retargeting campaign was better than that of the non-retargeting campaigns. Also, the ratio of cost to the successful purchase tag was higher for the product retargeting campaigns.

This study contributes to the literature of retargeting. First, this study provides SMEs with a successful roadmap for retargeting campaigns. Second, this research reveals the effectiveness and mechanism of retargeting for SMEs.