User Features Research Articles

From genies performing magic to sages imparting wisdom: a value-centred survey of music AI user interfaces, creative affordances and artist objectives

There are, at present, multiple fronts of debate about the ethics of Commercial Creative AI (ComCAI) product development. The issues of copyright and the right to know the AI provenance of work are dominant and well-defined. Meanwhile, a significant area of debate is trickier to define and analyse, relating to ComCAI's impact on the intrinsic values and virtues of human creative endeavour. In this paper, I analyse this impact by surveying the emerging landscape of user interfaces (UIs) in the domain of commercial music AI products. I do this through a value-centred design lens, considering how it is possible to articulate intrinsic values in the arts. Specifically, I select two artistic objectives: the need for creative artists to create works that are differentiated from others; the need for deep cognitive creative engagement with the work being created. I ask how ComCAI UIs can enable these artistic objectives, first through a survey of UI types and their combination in products, second through user feature requests. This design analysis tentatively suggests that those ComCAI tools promising to support artists increasingly need to provide greater control, in order to satisfy their creative users, and this is focussed towards either simply allowing post-generation editing, or improving generative control, which is in tension with the opaque nature of the generative systems. I propose that a value-centred design approach that highlights values such as differentiation and creative engagement helps to identify under-explored design spaces which have the potential to make better music AI experiences.

Repositories of Research Data in Russia and Abroad

One of the effective tools for providing open access to academic research results are repositories of various types. The most common are thematic, national, research and institutional repositories that usually contain text materials: monographs, scientific publications, conference proceedings, etc. In addition to the types mentioned above, thematic and universal research data repositories have been actively developed abroad in recent years. Besides text information, they also include numerical, audiovisual data, datasets, models, computer codes, etc. In order to assess the current state of data repositories in our country, we have conducted a study of websites of scientific organizations of the three categories that were approved by the Federal Agency for Scientific Organizations, in accordance with the Decree of the Government of the Russian Federation of April 8, 2009 No. 312 “On the Assessment and Monitoring of the Effectiveness of Scientific Organizations Performing Research, Development and Technological Work for Civil Purposes” as well as of educational institutions that are participants of the program “Priority 2030”. This work has identified only three educational institution’s data repositories, the content of which is mostly closed for a remote user. Among scientific institutions, information on research data was found on 20 websites. However, most of this information is presented as a list of data, without providing search options by various attributes and managing their results. In the meantime, we have found successful examples of functioning of Russian data repositories that include unique collections of scientific research and provide open access to the research results. They provide extensive search features for a remote user: possibilities of applying logical operators and faceted navigation, as well as sorting of search results. It has been found out that national data repositories are practically not covered in international aggregators, and the existing information about them is often incorrect. This has a negative impact on the visibility of research results within the global scientific community. At the same time, placing research data in repositories and making data repositories available in international aggregators promote visibility, accessibility and rapid distribution of research results. This eliminates the need for re-collection of data and prevents duplication of works.

NRDPA: Review-Aware Neural Recommendation with Dynamic Personalized Attention

Review-based recommendation can utilize user and item features extracted from review text to alleviate the problems of data sparsity and poor interpretability. However, most existing methods focus on static modeling of user personality and item attributes while ignoring the dynamic changes of user and item features. Therefore, this paper proposes a neural recommendation method with dynamic personalized attention (NRDPA). First, this method captures the changes in user behavior at the word level and review level and models the personalized features of users and items by dynamically highlighting key words and important reviews. Second, the method considers information interaction in the process of user and item modeling and adjusts the feature representations of the interacting parties according to the user’s preferences for different items. Finally, experiments on five public datasets from Amazon demonstrate that the proposed NRDPA model has superior performance, with improvements of up to 10% in MSE and 6.3% in MAE compared to state-of-the-art models.

Community Detection Framework Using Deep Learning in Social Media Analysis

Social media analysis aims to collect and analyze social media user information and communication content. When people communicate through messages, phone calls, emails, and social media platforms, they leave various records on their devices and the Internet, forming a huge social network. Community detection can help investigators analyze group leaders and community structure, which is significant to further crime control, identifying coordinated campaigns, and analyzing social network dynamics. This paper proposes the application of deep learning methods for community detection. Our main idea is to utilize social network topology and social network communication content to construct user features. The proposed end-to-end community detection framework is the implementation of Graph Convolution Network and can display the social network topology, locate the core members of the community, and show the connections between users. We evaluate our framework on the Enron email dataset. Experimental results indicate that our proposed model achieves a 1.1% higher modularity score than the unsupervised benchmark methods. We also concluded that the community detection framework should be able to analyze social networks, enabling investigators to reveal connections between people.

Personalized and Culturally Tailored Features of Mobile Apps for Gestational Diabetes Mellitus and Their Impact on Patient Self-Management: Scoping Review.

Gestational diabetes mellitus (GDM) is an increasingly common high-risk pregnancy condition requiring intensive daily self-management, placing the burden of care directly on the patient. Understanding personal and cultural differences among patients is critical for delivering optimal support for GDM self-management, particularly in high-risk populations. Although mobile apps for GDM self-management are being used, limited research has been done on the personalized and culturally tailored features of these apps and their impact on patient self-management. This scoping review aims to explore the extent to which published studies report the integration and effectiveness of personalized and culturally tailored features in GDM mobile apps for patient self-management support. We examined English-language peer-reviewed articles published between October 2016 and May 2023 from PubMed, CINAHL, PsycINFO, ClinicalTrials.gov, Proquest Research Library, and Google Scholar using search terms related to digital tools, diabetes, pregnancy, and cultural tailoring. We reviewed eligible articles and extracted data using the Arskey and O'Malley methodological framework. Our search yielded a total of 1772 articles after the removal of duplicates and 158 articles for full-text review. A total of 21 articles that researched 15 GDM mobile apps were selected for data extraction. Our results demonstrated the stark contrast between the number of GDM mobile apps with personalized features for the individual user (all 15 mobile apps) and those culturally tailored for a specific population (only 3 of the 15 mobile apps). Our findings showed that GDM mobile apps with personalized and culturally tailored features were perceived to be useful to patients and had the potential to improve patients' adherence to glycemic control and nutrition plans. There is a strong need for increased research and development to foster the implementation of personalized and culturally tailored features in GDM mobile apps for self-management that cater to patients from diverse backgrounds and ethnicities. Personalized and culturally tailored features have the potential to serve the unique needs of patients more efficiently and effectively than generic features alone; however, the impacts of such features still need to be adequately studied. Recommendations for future research include examining the cultural needs of different ethnicities within the increasingly diverse US population in the context of GDM self-management, conducting participatory-based research with these groups, and designing human-centered mobile health solutions for both patients and providers.

Cross-social-network user alignment research based on multi-dimensional user features

Accurately aligning the same users on different flat social networks to merge user information and create more nuanced user profiles is critical. However, the current research in this area faces challenges related to low efficiency and inadequate alignment accuracy. To address these challenges, we introduce a cross-social network user alignment model based on multi-dimensional user features (MDUF). First, inspired by the principles of entity recognition and Hartley's association method, we employed a block matrix association algorithm to project the original dataset into different high-dimensional spaces. Second, we proposed a new inertia weight calculation method to improve the convergence speed from linear to nonlinear transformations. This method improves the performance of traditional particle swarm optimization algorithms. Finally, we utilize improved particle swarm optimization and residual connection techniques to optimize bidirectional long short-term memory networks. The experimental results show that our proposed model significantly outperforms traditional alignment models in terms of alignment efficiency and accuracy, which is highly practical and has the potential to inspire further research on social network user alignment.

Operational Planning of TITIP: Entrust Services Mobile Platform Application

The high consumerism and instant lifestyle of Indonesian urban society has driven the growth of Amanah Jastip Service business which offers solutions for those who want to get goods without having to come to a physical location. The increasing number of internet and e-commerce users in Indonesia, especially in Java, further strengthens the market potential of the digital Jastip platform. However, many Jastip platforms in Indonesia have stagnated in feature development, which ends in negative user reviews and declining interest from new users. To answer this challenge, this study designed the TITIP application, a Jastip platform that emphasizes innovative features for users and service providers, such as integrated location maps, cost negotiation options, various payment methods, delivery services, and advertising features for service providers. This application aims to create an information technology-based solution that not only provides convenience but also has the potential to increase profitability, market position, and productivity. This research is expected to contribute to the development of the Jastip industry in Indonesia by answering technical challenges and meeting the growing needs of users. Through sustainable technology optimization and business strategies, the TITIP platform is expected to be a pioneer in providing effective services that meet the needs of modern consumers while encouraging the growth of the digital economy in Indonesia.

Let long-term interests talk: An disentangled learning model for recommendation based on short-term interests generation

In e-commerce recommendation systems, users’ long-term and short-term interests jointly influence product selection. However, the behavioral conformity phenomenon tends to be more prominent in short-term sequences, and the entanglement of true preference and popularity conformity data confuses the user’s real interest needs. To address this issue, we propose a sequential recommendation model called DFRec to disentangle short-term interests from popularity bias. By leveraging long-term interest trends, the model promotes the separation of short-term interests from popularity-driven deviations, thereby reducing the impact of popularity interference in short-term sequences. Firstly, we propose a Disentangled Frequency Attention Network(DFAN) to address the entanglement between real sequence features and conformity data in users’ short-term behavioral sequences. The approach clarify the non-entangled representation of the user’s short-term interest and conformity on the basis of long-term interest trends. Secondly, in order to capture the real long-term interest characteristics of users, this paper suggests using a Learnable Filter(LF) to filter the noise frequencies in long-term sequence. The method decouples the horizontal and vertical directions of the sequence and filters out the noise in both directions. Finally, consider the importance of the two interests characteristics is dynamic, we propose a joint learning framework with dual embeddings to balance and fusion these two features of users’ interests. Experimental results on three public datasets demonstrate that our model effectively captures dynamic user interests and outperforms six baseline models.

Explainable next POI recommendation based on spatial–temporal disentanglement representation and pseudo profile generation

The current research in Point-of-Interest (POI) recommendation primarily aims to decipher users’ transitional patterns to predict their future location visits. Traditional approaches often intertwine various features to model these check-in transitions, which inadvertently compromises the quality of the resulting representations. This issue is compounded in both industrial and academic settings, where user-generated textual data is frequently inaccessible or restricted due to privacy concerns. Such limitations in user profiles pose significant challenges to the effectiveness of subsequent applications. In response to these challenges, the recent rise of Large Language Models (LLMs) offers a novel perspective. Diverging from the conventional approach of leveraging LLMs for semantic-based next check-in predictions, our research investigates the potential of integrating LLMs with sequential recommendation systems. This integration aims to augment feature dimensions and facilitate the generation of explicit explanations. To this end, we introduce CrossDR-Gen, a Cross-sequence Location Disentanglement Representation methodology. CrossDR-Gen is specifically designed for next POI recommendation and explanation generation. It uniquely considers spatial and temporal factors in shaping check-in behaviors, offering a comprehensive global view of location transitions. Crucially, CrossDR-Gen utilizes LLMs for pseudo profile generation in scenarios with limited semantic context, thereby enriching user features without relying on additional textual profiles or conversational data. Our experiments on real-world datasets demonstrate that CrossDR-Gen not only excels in addressing cold-start scenarios but also showcases robust recommendation capabilities. These findings validate the effectiveness of our proposed cooperative paradigm between LLMs and sequential recommendation models, highlighting a promising avenue for future research in POI recommendation systems.

SingletSeeker: an unsupervised clustering approach for automated singlet discrimination in cytometry.

Flow cytometry is a high-throughput, high-dimensional technique that generates large sets of single-cell data. Prior to analyzing this data, it is common to exclude any events that contain two or more cells, multiplets, to ensure downstream analysis and quantification is of single-cell events, singlets, only. The process of singlet discrimination is critical yet fundamentally subjective and time-consuming; it is performed manually by the user, where the proper exclusion of multiplets depends on the user's expertise and often varies from experiment to experiment. To address this problem, we have developed an algorithm to automatically discriminate singlets from other unwanted events such as multiplets and debris. Using parameters derived from imaging, the algorithm first identifies high-density clusters of events using a density-based clustering algorithm, and then classifies the clusters based on their properties. Multiplets are discarded in the first step, while singlets are distinguished from debris in the second step. The algorithm can use different strategies on imaging feature selection-based user's preferences and imaging features available. In addition, the relative importance of singlets precision vs. sensitivity can be further tweaked via a density coefficient adjustment. Twenty-two datasets from various sites and of various cell types acquired on the BD FACSDiscover™ S8 Cell Sorter with CellView™ Image Technology were used to develop and validate the algorithm across multiple imaging feature sets. A consistent singlets precision >97% with a solid >88% sensitivity has been demonstrated with a LightLoss feature set and the default density coefficient. This work yields a high-precision, high-sensitivity algorithm capable of objective and automated singlet discrimination across multiple cell types using various imaging-derived parameters. A free FlowJo™ Software plugin implementation is available for simple and reproducible singlet discrimination for use at the beginning of any user's workflow.

Designing User Experience for a Mobile Application for Agricultural Product Marketing Using the Human-Centered Design Method

This research explores the application of Human-Centered Design (HCD) in developing a mobile application for agricultural product marketing, aiming to address critical challenges faced by farmers, such as limited market access and inconsistent internet connectivity. By involving farmers and consumers in each stage of the design process, the application was iteratively improved based on user feedback. The study implemented low-fidelity and high-fidelity prototyping, with five iterations of user testing to enhance usability, navigation, and accessibility. Results show a significant increase in task success rates, user satisfaction, and application efficiency, mainly by including offline features for users in areas with poor internet infrastructure. The study also highlights the effectiveness of HCD in adapting technology to local conditions, offering a practical solution that supports the digital transformation of the agricultural sector, particularly in rural areas. This research contributes to the literature by demonstrating that HCD can be effectively used to develop user-friendly applications that meet the specific needs of the agricultural community

The short video platform recommendation mechanism based on the improved neural network algorithm to the mainstream media

Currently, the capacity of short videos continues to increase. Video manufacturers hope to enhance user experience and stickiness through recommendation algorithms, while users seek personalized videos to save time and money. Therefore, in order to address the data sparsity and high-dimensional feature extraction, this study proposes a novel short video platform recommendation model. The proposed method utilizes the term frequency inverse document frequency algorithm for text mining, and combines error back propagation neural network for learning to explore the potential connection between users and videos. This method combines natural language processing and image analysis in deep learning to construct accurate user and video models, deeply explore user interests, and improve the accuracy and effectiveness of recommendation systems for user preferences. The research results showed that the recommendation accuracy of this method was 66 % and 70 % respectively, and the prediction accuracy was 73.50 % and 88 % respectively. When Num = 128, 200 data points were recommended within 0.3678 s. The proposed algorithm outperforms the other three methods in terms of recommendation accuracy compared with the ItemCF and UserCF algorithms. This is because the method uses an approach based on image and user vector, combined with relevant features of the video and user. The proposed method can deeply explore the relevant features of videos and users, overcoming the data scarcity in previous collaborative screening, and guiding video recommendation on practical media platforms.

Granular intents learning via mutual information maximization for knowledge-aware recommendation

Knowledge-aware recommender systems, which utilize knowledge graphs (KGs) to enrich item information, have been shown to improve the accuracy and explainability of recommendations. Besides, KGs are further explored to determine the intent of choosing items (i.e., the reason why users select items of interest). Conventional methods represent intents either as sets of relations in a KG or as KG entities. However, such approaches fail to fully leverage the combined information provided by both entities and relations. To address this issue, we propose a new KG-based user Intent Extraction Framework (KIEF) to capture user intents at a more fine-grained level for recommendation. Specifically, we propose a novel intent representation constructed with relation-aware entity representation, encouraging finer granularity for user intents. Furthermore, since a KG may contain noisy information that impairs the quality of user intent, it is compulsory to consider which factors in a KG are important to represent a user’s intent. Thus, we introduce global intent which are comprehensive features for the entire interactions of all users and local intent, which are empirical features of individual users from personal history. By maximizing mutual information between global and local intents, KIEF captures user preference for items. Through extensive experiments on four real-world benchmark datasets, we prove the superior performance of KIEF over the state-of-the-art and analyze interpretable explanations for understanding user intents.

Movie Recommendation System Based on Word Embedding

Abstract. Amidst the swift progression of Internet and big data technologies, recommendation systems have emerged as crucial conduits linking users to products across various digital platforms. This study delves into the deployment of neural collaborative filtering within the realm of movie recommendation systems, with the objective of constructing a system of high precision. Utilizing the MovieLens dataset, this investigation applies one-hot encoding and embedding techniques within the PyTorch-Lightning framework to effectively model user behaviors and predict cinematic preferences. The neural collaborative filtering (NCF) model leverages deep learning to extract latent features of users and items, exhibiting a notable enhancement in performance compared to traditional collaborative filtering approaches. Empirical results indicate that the NCF model attains an accuracy of 86% on the validation dataset, underscoring its efficacy in extensive recommendation scenarios.

NCF-based Movie Recommendation System

Abstract. This paper discusses the design and evaluation of a Neural Collaborative Filtering (NCF) model for movie recommendations using the MovieLens dataset. It addresses the limitations of traditional recommendation systems, such as content-based filtering and collaborative filtering, which struggle with data sparsity and the cold start problem. By incorporating deep learning, the NCF model enhances the accuracy and personalization of recommendations by learning the latent features of users and items and capturing complex interactions.

A mixed-methods survey and focus group study to understand researcher and clinician preferences for a Journal transparency Tool

Transparency within biomedical research is essential for research integrity, credibility, and reproducibility. To increase adherence to optimal scientific practices and enhance transparency, we propose the creation of a journal transparency tool (JTT) that will allow users to obtain information about a given scholarly journal’s operations and transparency policies. This study is part of a program of research to obtain user preferences to inform the proposed JTT. Here, we report on our consultation with clinicians and researchers. This mixed-methods study was conducted in two parts. The first part involved a cross-sectional survey conducted on a random sample of authors from biomedical journals. The survey asked clinicians and researchers about the inclusion of a series of potential scholarly metrics and user features in the proposed JTT. Quantitative survey items were summarized with descriptive statistics. Thematic content analysis was employed to analyze text-based responses. Subsequent focus groups used survey responses to further explore the inclusion of items in the JTT. Items with less than 70% agreement were used to structure discussion points during these sessions. Participants voted on the use of user features and metrics to be considered within the journal tool after each discussion. Thematic content analysis was conducted on interview transcripts to identify the core themes discussed. A total of 632 participants (5.5% response rate) took part in the survey. A collective total of 74.7% of respondents found it either ‘occasionally, ‘often’, or ‘almost always’ difficult to determine if health information online is based on reliable research evidence. Twenty-two participants took part in the focus groups. Three user features and five journal tool metrics were major discussion points during these sessions. Thematic analysis of interview transcripts resulted in six themes. The use of registration was the only item to not meet the 70% threshold after both the survey and focus groups. Participants demonstrated low scholarly communication literacy when discussing tool metric suggestions. Our findings suggest that the JTT would be valuable for both researchers and clinicians. The outcomes of this research will contribute to developing and refining the tool in accordance with researchers and clinicians.

Enhancing Biometric Security with Bimodal Deep Learning and Feature-level Fusion of Facial and Voice Data

Recent research in biometric technologies underscores the benefits of multimodal systems that use multiple traits to enhance security by complicating the replication of samples from genuine users. To address this, we present a bimodal deep learning network (BDLN or BNet) that integrates facial and voice modalities. Voice features are extracted using the SincNet architecture, and facial image features are obtained from convolutional layers. Proposed network fuses these feature vectors using either averaging or concatenation methods. A dense connected layer then processes the combined vector to produce a dual-modal vector that encapsulates distinctive user features. This dual-modal vector, processed through a softmax activation function and another dense connected layer, is used for identification. The presented system achieved an identification accuracy of 99% and a low equal error rate (EER) of 0.13% for verification. These results, derived from the VidTimit and BIOMEX-DB datasets, highlight the effectiveness of the proposed bimodal approach in improving biometric security.

UeLP: accurate user linkage across social platforms against location errors

Abstract User linkage across social platforms can connect the accounts of the same user across different social networks, which is crucial for the identification of users’ multiple social identities and cross-platform association analysis. Cross-platform user linkage based on location is a typical method in current research. These methods typically rely on check-in data to calculate user similarity. However, different from check-in location, the location data obtained from instant messaging social platforms may contain random errors, leading to low accuracy of user linkage of such methods. To solve this problem, this paper proposes an accurate user linkage method across social platforms against location errors. First, unlike existing methods that employ fixed-size grids, this paper uses a multi-grained spatio-temporal grid to organize data, in order to accurately extract user features from error locations. Then, by extracting coarse-grained movement pattern features from user trajectories, candidate users are filtered out, and a small subset of candidate uses is generated to effectively reduce the search space. Next, we establish a weight model based on grid contribution and motion sequence similarity to extract location and temporal features with stronger user orientation. Finally, according to the weight model, the weighted cluster center distance of trajectories is used to calculate the similarity between two different user trajectories. The user with the highest similarity is selected from the candidate subset to complete the user linkage. The extensive experiments are conducted on six public datasets containing 115 866 trajectories and a self-built dataset with 5358 trajectories. The results show the following: compared with the four existing typical location-based methods $k$-BCT, GS, TF-IDF, and TF-IWF, the accuracy Acc@1 is improved by an average of 33%, 44.94%, 15.2%, and 14.55%, respectively, and the accuracy Acc@3 is improved by 30.52%, 34.67%, 13.84%, and 13.19%, respectively.

Combining style generative adversarial networks with particle swarm optimisation-support vector regression to design affective social robot for public health intervention

In order to improve the attractiveness of social robot serving health interventions in public workspace, we propose a product design method with the combination of Style-generative adversarial network (StyleGAN) model and particle swarm optimisation-support vector regression (PSO-SVR). This paper aims to explore the modelling generation method of social robots for health intervention based on artificial intelligence generated content (AIGC) and a mapping model between the shape characteristics and users’ visual perception based on Kansei Engineering (KE). Firstly, to address the defects of typical KE over-reliance on existing samples, we introduce the StyleGAN model in AIGC to learn and train existing robots’ shape samples and generate new robots’ shape sample images. Secondly, the morphological deconstruction method is used to deconstruct the shape features of the new robot sample. Factor analysis (FA) is also used to reduce dimension and cluster emotional words and establish a Likert scale between the shape features of robots and users’ emotional vocabulary. Finally, particle swarm optimisation-support vector regression (PSO-SVR) is used to establish a mapping model between the shape features of social robots and the emotional images of users, thus obtaining the most attractive shape combination scheme. The research results showed that the StyleGAN model in AIGC can be used to assist industrial designers in creative expression and provide rich sample sources for KE; and the PSO-SVR of machine learning can be used to build a mapping model among users’ visual feelings, emotional images and shape features. In the end, we designed an attractive social robot for public health intervention.

Analysis of Software Developers' Programming Language Preferences and Community Behavior From Big5 Personality Traits

ABSTRACTMany programming languages and technologies have appeared for the purpose of software development. When choosing a programming language, the developers' cognitive attributes, such as the Big5 personality traits (BPT), may play a role. The developers' personality traits can be reflected in their social media content (e.g., tweets, statuses, Q&A, reputation). In this article, we predict the developers' programming language preferences (i.e., the pattern of picking up a language) from their BPT derived from their content produced on social media. We randomly collected data from a total of 820 Twitter (currently X) and Stack Overflow (SO) users. Then, we collected user features (i.e., BPT, word embedding of tweets) from Twitter and programming preferences (i.e., programming tags, reputation, question, answer) from SO. We applied various machine learning (ML) and deep learning (DL) techniques to predict their programming language preferences from their BPT. We also investigated other interesting insights, such as how reputation and question‐asking/replying are associated with the users' BPT. The findings suggest that developers with high openness, conscientiousness, and extraversion are inclined to mobile applications, object‐oriented programming, and web programming, respectively. Furthermore, developers with high openness and conscientiousness traits have a high reputation in the SO community. Our ML and DL techniques classify the developers' programming language preferences using their BPT with an average accuracy of 78%.