A Framework for Feature Selection using Natural Language Processing for User Profile Learning for Recommendations of Healthcare Related Content

This paper presents the work done on recommendations of healthcare related journal papers by understanding the semantics of terms from the papers referred by users in past. In other words, user profiles based on user interest within the healthcare domain are constructed from the kind of journal papers read by the users. Multiple user profiles are constructed for each user based on different categories of papers read by the users. The proposed approach goes to the granular level of extrinsic and intrinsic relationship between terms and clusters highly semantically related relevant domain terms where each cluster represents a user interest area. The semantic analysis of terms is done starting from co-occurrence analysis to extract the intra-couplings between terms and then the inter-couplings are extracted from the intra-couplings and then finally clusters of highly related terms are formed. The experiments showed improved precision for the proposed approach as compared to the state-of-the-art technique with a mean reciprocal rank of 0.76.

Are Topics Interesting or Not? An LDA-based Topic-graph Probabilistic Model for Web Search Personalization

In this article, we propose a Latent Dirichlet Allocation– (LDA) based topic-graph probabilistic personalization model for Web search. This model represents a user graph in a latent topic graph and simultaneously estimates the probabilities that the user is interested in the topics, as well as the probabilities that the user is not interested in the topics. For a given query issued by the user, the webpages that have higher relevancy to the interested topics are promoted, and the webpages more relevant to the non-interesting topics are penalized. In particular, we simulate a user’s search intent by building two profiles: A positive user profile for the probabilities of the user is interested in the topics and a corresponding negative user profile for the probabilities of being not interested in the the topics. The profiles are estimated based on the user’s search logs. A clicked webpage is assumed to include interesting topics. A skipped (viewed but not clicked) webpage is assumed to cover some non-interesting topics to the user. Such estimations are performed in the latent topic space generated by LDA. Moreover, a new approach is proposed to estimate the correlation between a given query and the user’s search history so as to determine how much personalization should be considered for the query. We compare our proposed models with several strong baselines including state-of-the-art personalization approaches. Experiments conducted on a large-scale real user search log collection illustrate the effectiveness of the proposed models.

Learning a Hierarchical Intent Model for Next-Item Recommendation

A session-based recommender system (SBRS) captures users’ evolving behaviors and recommends the next item by profiling users in terms of items in a session. User intent and user preference are two factors affecting his (her) decisions. Specifically, the former narrows the selection scope to some item types, while the latter helps to compare items of the same type. Most SBRSs assume one arbitrary user intent dominates a session when making a recommendation. However, this oversimplifies the reality that a session may involve multiple types of items conforming to different intents. In current SBRSs, items conforming to different user intents have cross-interference in profiling users for whom only one user intent is considered. Explicitly identifying and differentiating items conforming to various user intents can address this issue and model rich contextual information of a session. To this end, we design a framework modeling user intent and preference explicitly, which empowers the two factors to play their distinctive roles. Accordingly, we propose a key-array memory network (KA-MemNN) with a hierarchical intent tree to model coarse-to-fine user intents. The two-layer weighting unit (TLWU) in KA-MemNN detects user intents and generates intent-specific user profiles. Furthermore, the hierarchical semantic component (HSC) integrates multiple sets of intent-specific user profiles along with different user intent distributions to model a multi-intent user profile. The experimental results on real-world datasets demonstrate the superiority of KA-MemNN over selected state-of-the-art methods.

The Learning Style of Gamers

The use of gamification has shown to be an interesting approach to engage users in MOOCs. In this context, different game strategies, elements, and mechanics are applied to help to improve the teaching/learning process. When designing teaching/learning methods, teachers must take into account both gamification techniques and learning styles in order to encourage students and to improve their learning performance, respectively. However, while applying gamification and at the same time keep taking into account the corresponding learning styles, we may find some kinds of incompatibilities. Thus, what this chapter covers is the conducted experimental analysis aimed at exploring the viability of merging gamer's profiles and learning styles in a single multidimensional user profile. The obtained results expose that, with this approach, we are able to identify groups of students so that, while designing teaching/learning methods, we can take into account both learning styles to improve the learning performance and gamification techniques to motivate and encourage the student.

OUPIP

This article aims to propose an ontological user model called OUPIP (Ontology-Based User Profile for Impairment Person), that extends existing ontologies to help designers and developers to adapt applications and devices according to the user's profile, disability and dynamic context. Besides, the approach has been applied in a typical real-life scenario in which personalized services are provided to impairment person through a mobile phone.

Profiling Digital Printing Technology Adoption in the Fashion Industry: A New Approach to Exploring Innovation Diffusion

Digital printing technology (DPT) represents a core innovation that is currently revolutionizing the global decorated apparel market by automating the printing process, facilitating customization, and reducing energy costs and production lead time. However, the fundamental understanding of the emerging DPT market remains unexplored due to its novelty. This study aims to identify DPT diffusion patterns over the past decade in the U.S. market and establish a predictive user profile employing social media-based analytics along with data mining and traditional statistical modeling. A proxy variable is used to measure likely adoption which reflects an S-shaped diffusion curve consistent with Diffusion of Innovations Theory. Additionally, the outcome profile suggests that likely DPT adopters reside in locations that reflect higher levels of education (bachelor’s degrees or higher), relatively young populations (i.e. between 19–34 years of age), proportionately higher incomes generated from art and design occupations, but with lower household annual incomes.

eHealth and mHealth Development in Spain: Promise or Reality?

In the last decades, the use of Information and Communication Technologies (ICTs) has progressively spread to society and public administration. Health is one of the areas in which the use of ICTs has more intensively developed through what is now known as eHealth. That area has recently included mHealth. Spanish health system has stood out as one of the benchmarks of this technological revolution. The development of ICTs applied to health, especially since the outbreak of the pandemic caused by SARS Cov-2, has increased the range of health services delivered through smartphones and the development of subsequent specialized apps. Based on the data of a Survey on Use and Attitudes regarding eHealth in Spain, the aim of this research was to conduct a comparative analysis of the different eHealth and mHealth user profiles. The results show that the user profile of eHealth an mHealth services in Spain is not in a majority. Weaknesses are detected both in the knowledge and use of eHealth services among the general population and in the usability or development of their mobile version. Smartphones can be a democratizing vector, as for now, access to eHealth services is only available to wealthy people, widening inequality.

Real-time bidding campaigns optimization using user profile settings

Real-Time bidding is nowadays one of the most promising systems in the online advertising ecosystem. In the presented study, the performance of RTB campaigns is improved by optimising the parameters of the users’ profiles and the publishers’ websites. Most studies about optimising RTB campaigns are focused on the bidding strategy; estimating the best value for each bid. However, our research is focused on optimising RTB campaigns by finding out configurations that maximise both the number of impressions and the average profitability of the visits. An online campaign configuration generally consists of a set of parameters along with their values such as {Browser = “Chrome”, Country = “Germany”, Age = “20–40” and Gender = “Woman”}. The experiments show that, when the number of required visits by advertisers is low, it is easy to find configurations with high average profitability, but as the required number of visits increases, the average profitability diminishes. Additionally, configuration optimisation has been combined with other interesting strategies to increase, even more, the campaigns’ profitability. In particular, the presented study considers the following complementary strategies to increase profitability: (1) selecting multiple configurations with a small number of visits rather than a unique configuration with a large number of visits, (2) discarding visits according to certain cost and profitability thresholds, (3) analysing a reduced space of the dataset and extrapolating the solution over the whole dataset, and (4) increasing the search space by including solutions below the required number of visits. The developed campaign optimisation methodology could be offered by RTB and other advertising platforms to advertisers to make their campaigns more profitable.

Positive effect of combined exercise on adipokines levels and pubertal signs in overweight and obese girls with central precocious puberty

Background The prevalence of precocious puberty is increasing. Obesity has been demonstrated to be associated with changes in the adipokine profile and incidence of early puberty in girls. This study assessed the pubertal signs, the levels of adiponectin, resistin, and tumor necrosis factor-alpha (TNF-α) after 12 weeks of combined exercise and 4 weeks of detraining in overweight and obese girls with precocious puberty. Methods Thirty overweight and obese girls (aged 7–9) with precocious puberty, who had received Triptorelin, were randomly divided into two groups (15 exercise and 15 control). Initially, serum levels of adiponectin, resistin, TNF-α, luteinising hormone (LH), and follicle-stimulating hormone (FSH) and the signs of puberty progression (bone age, uterine length, and ovarian volume) were measured. The exercise group performed 60 min of combined (aerobic and resistance) exercise three times/week for 12 weeks. The control group did not receive any exercise. 48 h after the last training session and after 4 weeks of detraining, all research variables were measured (also in the control group). The statistical method used for data analysis was repeated measures ANOVA. Results In the exercise group, adiponectin significantly increased and resistin significantly decreased after 12 weeks. After 4 weeks of detraining, adiponectin significantly decreased, but resistin significantly increased. TNF-α levels did not change significantly during the study. There was no significant difference in all of the factors in the control group. Throughout the 16-week study period, the rate of puberty and LH significantly decreased in both exercise and control groups, but FSH, LH/FSH and ovarian volume significantly decreased in the exercise group alone (P<0.05). Conclusions Combined exercise increased adiponectin and decreased resistin and the rate of puberty. However, after 4 weeks of detraining, these effects diminished but did not disappear. Trial registration IRCT, IRCT56471. Registered 25 may 2021 - Retrospectively registered, https://fa.irct.ir/user/profile