User Profiles Research Articles

Increasing age and lethal opiate use.

Opioid abuse is a leading cause of drug-related morbidity and mortality worldwide. It has been suggested that the age of opiate users in Australia is rising. To evaluate this further in a local population, toxicology and pathology case files from Forensic Science SA, Adelaide, South Australia, were examined for all cases with lethal opioid levels from 2000 to 2019 (n = 499; M:F 2.3:1; age range 18-91 years, median age 42 years). The median age of opiate deaths increased significantly by approximately 16 years (p = 0.007, R2 = 0.34) with a significant increase in total deaths in the 45-54 years and 55-64 years age groups (p = 0.009, R2 = 0.32) (p = < 0.001, R2 = 0.54). Deaths due to heroin overdose showed the lowest median age (39 years, n = 184), with deaths from tramadol toxicity having the highest (50.5 years, n = 32). Recent changes in the demographic profile of opioid users in cases of lethal overdose involve an aging population. Forensic and clinical practitioners should be aware of significant opioid abuse in certain individuals at older ages as this raises the possibility that this may exacerbate the effects of age-related chronic diseases in this group and/or contribute to fatalities.

The social force model: a behavioral modeling approach for information propagation during significant events

Information diffusion otherwise known as the propagation, spread or dissemination of information occurs when a piece of information flows from a particular individual/community to another in a social network. Studies related to information propagation involve problems regarding the factors that affect the information propagation, how the information is disseminated, the speed of propagation, etc. Researchers have proposed information propagation models to understand the phenomenon and to answer these questions. These models have been effectively used in applications such as behavior analysis, public health care, etc. Although several studies are carried out in this field, the literature demands identifying the most influential factors of propagation in real time in cases of sudden unexpected significant disasters/epidemics/pandemics, since the existing propagation models seem unfit during such circumstances. In this paper, a novel information propagation model which predicts the top propagators of information related to a particular context is proposed. This model utilizes the past few weeks' data during a sudden outbreak of a disaster and identifies the most influential attributes of a user profile to predict the top propagators of the future. The proposed Social Force Model is inspired by a model used in studying the fear propagation pattern in pedestrian dynamics in real-life situation [Cornes FE, Frank GA, Dorso CO. Fear propagation and the evacuation dynamics. Simul Model Pract Theory. 2019;95:112–133.]. We have effectively mapped the various forces which constitute the Social Force Model such as the Desired Force, the Social Force and the Granular Force with respect to the online social network context in order to discover the key spreaders of information during a specific context. Apart from identifying the propagators, the proposed model discovers the key attributes by analyzing the behavior of users based on their past activities in the online social network.

Data-Driven Personalized Marketing in E-commerce: Practical Applications

Data-driven personalized marketing is crucial for enhancing user experience and increasing sales in e-commerce. This paper explores the practical applications of personalized marketing, focusing on algorithms, user behavior analysis, and associated risks. Also, the paper illustrates how data-driven personalized marketing is implemented and its impact on user engagement and sales. The collection and processing of large amounts of user data are essential for personalized marketing strategies. Various algorithms, including collaborative filtering and deep learning, are employed for personalized recommendation systems. Real-time data analysis techniques enable e-commerce companies to adjust marketing strategies rapidly. Combining information from several platforms, including social media, mobile apps, and websites helps in creating comprehensive user profiles for effective personalized marketing. Analyzing user behavior is essential to comprehending user requirements and preferences. However, there are risks and challenges associated with data-driven personalized marketing, including data privacy and compliance issues, over-personalization risks, and data quality concerns.

Comparing location-specific and location-open social media data: methodological lessons from a study of blaming of minorities on Twitter during the COVID-19 pandemic

Social media platforms such as Twitter (currently X) have become important sites of public discourse and participation. Researchers have attempted to identify and collect Twitter data within a certain country or region in order to answer research questions within a particular locale. However, location information of tweets is limited. Tackling the case of public blaming of minorities on Twitter in the context of the COVID-19 pandemic in the UK, we present a method for identifying UK-based tweets and analyse two types of datasets that we collected and processed: (a) tweets with UK location-tags (labelled as location-specific data and referred to as UK datasets); and (b) tweets with UK location-tags and / or user profiles containing potential UK location information (labelled as location-open data and referred to as ALL datasets). The empirical results reveal that the overall sentiments in the two dataset types align in the same direction, but the location-specific datasets contain more extreme discourses (i.e., more positive and more negative sentiments and fewer neutral sentiments). Furthermore, in the location-specific datasets, the range of theme areas is narrower, although the themes still grasp the essence of the discussion about blaming minorities found in the larger dataset. The findings demonstrate strengths and limitations of the two dataset types and that the location-specific data can be suitable especially when the available research resources are insufficient for collecting or processing larger datasets. Nevertheless, we propose that future research may consider comparing smaller and bigger datasets to test differences between these for other topics for which specific locations may be of particular interest.

Natural language processing for analyzing online customer reviews: a survey, taxonomy, and open research challenges.

In recent years, e-commerce platforms have become popular and transformed the way people buy and sell goods. People are rapidly adopting Internet shopping due to the convenience of purchasing from the comfort of their homes. Online review sites allow customers to share their thoughts on products and services. Customers and businesses increasingly rely on online reviews to assess and improve the quality of products. Existing literature uses natural language processing (NLP) to analyze customer reviews for different applications. Due to the growing importance of NLP for online customer reviews, this study attempts to provide a taxonomy of NLP applications based on existing literature. This study also examined emerging methods, data sources, and research challenges by reviewing 154 publications from 2013 to 2023 that explore state-of-the-art approaches for diverse applications. Based on existing research, the taxonomy of applications divides literature into five categories: sentiment analysis and opinion mining, review analysis and management, customer experience and satisfaction, user profiling, and marketing and reputation management. It is interesting to note that the majority of existing research relies on Amazon user reviews. Additionally, recent research has encouraged the use of advanced techniques like bidirectional encoder representations from transformers (BERT), long short-term memory (LSTM), and ensemble classifiers. The rising number of articles published each year indicates increasing interest of researchers and continued growth. This survey also addresses open issues, providing future directions in analyzing online customer reviews.

User segmentation in human–robot interactions: insights from sports betting patrons using diffusion of innovation theory

ABSTRACT Previous research has assumed uniformity in user response to service robots regardless of user profile. This study sought to understand the nature of human–robot interactions in a competitive setting by applying the diffusion of innovation theory. Through a survey of 447 sports betting patrons, we used unsupervised learning to cluster the patrons based on human/robot interaction, relational and psychological variables, usage intention, and socioeconomic information. Four clusters were identified: Tech laggards, Optimists, Skeptics, and Enthusiasts. Trust was a key determining factor of cluster membership, especially among frequent betters. Further, the study examined each cluster through the lens of psychological theories and ethical perspectives, identified associated risks, and offered mitigation strategies. Practical implications are discussed.

Social media’s dark secrets: A propagation, lexical and psycholinguistic oriented deep learning approach for fake news proliferation

Most existing methods for detecting fraudulent news or other forms of disinformation primarily rely on user profiling or content analysis, determining whether a given article aligns with a user’s stylistic or content-related preferences. This research departs from conventional approaches by concentrating not only on the characteristics of shared content but also on user interactions and the resultant topologies of content propagation trees. In our study, we have introduced a deep learning model based on Graph Convolutional Neural Networks (GCNN) and enhanced with multi-head attention mechanisms. This model leverages a wide range of psycholinguistic attributes extracted from users’ posts, including sentiment, emotional content, linguistic features, personality traits, readability, and communication style. We further enrich these attributes with BERT embeddings to improve textual representation. Our research framework involves creating two distinct graph networks: the user interaction graph and the semantic propagation graph. These graphical representations are essential for visualizing dynamic interactions and patterns of information dissemination among users. For each user, we generate a set of carefully crafted features that capture their unique characteristics and behaviors. These user-specific features are then integrated into the User Interaction Graph, enabling a more nuanced understanding and representation of user interactions within our proposed model. The proposed framework has demonstrated superior performance on benchmark datasets, achieving accuracies and precisions of 91.07% and 91.24% on the FakeNewsNet dataset, and 94.20% and 94.92% on the FibVid dataset, respectively. The results obtained from the experimental evaluation have also revealed the effect of various parameters significant to profile disinformers, signifying a substantial improvement in the field of fake news detection and profiling.

The rising use of cognitive enhancement drugs and predictors of use during COVID-19: findings from a cross-sectional survey of students and university staff in the UK.

The use of psychoactive substances to increase cognitive performance while studying has been termed 'pharmacological cognitive enhancement' (PCE). In previous years, several large-scale national surveys have focused on their use by students at university, including drug types, prevalence rates, and predictive factors. The recent coronavirus pandemic brought about widespread structural changes for UK universities, as students were forced to adapt to home-based learning and in many cases reduced academic support. No study has yet focused primarily on the impact of pandemic social restrictions on PCE in students and academic staff, and whether personality and demographic factors reveal user profiles that predict use during the pandemic period. A convenience sample of 736 UK students and staff aged 18-54 (M = 22.2, SD = 5.2) completed a cross-sectional survey assessing PCE prevalence rates, polydrug use, perceived effects, academic self-efficacy and personality during the first year of social restrictions (March 2020 - February 2021) compared with the previous year (March 2019 - February 2020). There was a significant self-reported rise in the use of all drug types (all ps < 0.001) during social restrictions, particularly with Modafinil (+42%), nutraceuticals (+30.2%) and microdose LSD (+22.2%). Respondents also indicated stronger PCE effects for all substances, except alcohol, in comparison to the previous year. Polydrug use with modafinil and other prescription stimulants increased the most during social restrictions. Personality factors and gender identity reliably predicted PCE use and lower agreeableness was often the strongest predictor, followed by identifying as male and lower conscientiousness. Academic self-efficacy and student/academic staff status were not consistent predictors. This is the first survey of UK students to investigate PCE during coronavirus social restrictions and to assess predictive factors. Findings reveal a rise in PCE use and polydrug use which we suggest is because of increased pressures on students created by the lockdown and reduced access to university resources.

ANDROID HEALTHCARE APPLICATION

The healthcare systems is pivotal in improving the accessibility and management of healthcare services. This paper focuses on the creation of a comprehensive appointment management system to streamline various healthcare interactions. Modern healthcare challenges such as scheduling appointments, ordering medications, and accessing health information necessitate an integrated approach. The proposed system includes modules for user registration, lab test management, medication management, doctor search and appointment booking, health education articles, order tracking, and user logout functionalities. Utilizing user-friendly interfaces and robust backend infrastructure, the system ensures secure user registration, easy browsing of lab tests and medications, efficient search for specialist doctors, convenient appointment booking, access to health articles, and order tracking. Key features include personalized user profiles, real-time appointment scheduling, and secure data storage using a SQLite database. Keywords: Healthcare management, Mobile Applications, Software Engineering

Transforming experimental radiology: Design and implementation of an innovative ePACS image storage system for AI imaging research environments

Introduction and purpose: We present the needs, design, development, implementation, and accessibility of a crafted experimental PACS (ePACS) system to securely store images, ensuring efficiency and ease of use for AI processing, specifically tailored for research scenarios, including phantoms, animal and human studies and quality assurance (QA) exams. The ePACS system plays a crucial role in any medical imaging departments that handle non-care profile studies, such as protocol adjustments and dummy runs. By effectively segregating non-care profile studies from the healthcare assistance, the ePACS usefully prevents errors both in clinical practice and storage security. Methods and results: The developed ePACS system considers the best practices for management, maintenance, access, long-term storage and backups, regulatory audits, and economic aspects. Moreover, key aspects of the ePACS system include the design of data flows with a focus on incorporating data security and privacy, access control and levels based on user profiles, internal data management policies, standardized architecture, infrastructure and application monitorization and traceability, and periodic backup policies. A new tool called DicomStudiesQA has been developed to standardize the analysis of DICOM studies. The tool automatically identifies, extracts, and renames series using a consistent nomenclature. It also detects corrupted images and merges separated dynamic series that were initially split, allowing for streamlined post-processing. Discussion and conclusions: The developed ePACS system encompasses a successful implementation, both in hospital and research environments, showcasing its transformative nature and the challenging yet crucial transfer of knowledge to industry. This underscores the practicality and real-world applicability of our innovative approach, highlighting the significant impact it has on the field of experimental radiology.

Patterns of Pregabalin Users from Substance Abuse Treatment Facilities: Results from the French OPPIDUM Program from 2008 to 2022.

In recent years, pregabalin has received growing attention due to its abuse liability. The aim of this study was to further characterize patterns of pregabalin users from substance abuse treatment facilities and detect changes in users profile over the study period. The data source was the Observation des Produits Psychotropes Illicites ou Détournés de leur Utilisation Médicamenteuse (OPPIDUM) program, an annual, repeated, cross-sectional, nationwide, multicenter survey that collects consumption data from patients with substance use disorders. First, we described the characteristics of pregabalin users and their consumption patterns. We compared these data between 2008 and 2018 (P1) and 2019 and 2022 (P2). Second, we conducted a multiple correspondence analysis to identify profiles of users. From 2008 to 2022, 291 pregabalin users (0.37% of all users) from 116 substance abuse treatment facilities were identified. The number of pregabalin users was lower than 15 per year in P1 (n = 89) and between 40 and 60 per year in P2 (n = 202). The number of users who reported pregabalin as the first substance leading to dependence increased significantly in P2 compared with P1 (p < 0.005). When comparing P2 with P1, there was a significant increase in precarity (p < 0.001), users in prison (p = 0.002), withdrawal symptoms (p < 0.001), dependence (p < 0.001), use of higher dose of pregabalin (p = 0.029), and acquisition by deal/street market (p < 0.001). The multiple correspondence analysis allowed for the identification of distinct profiles of pregabalin users: (i) a cluster with mainly users from P1, who presented a simple use of pregabalin, and were older (> 45 years), were involved in opioid agonist treatment (OAT), and obtained pregabalin legally; and (ii) a cluster with mainly users from P2, who presented pregabalin dependence, and were younger (< 26 years), reported pregabalin as the first substance leading to dependence, used doses higher than the market authorization, were in severe precarity, and were in prison. These data showed that the profile of pregabalin users has changed in the last years. Pregabalin use disorders also affect users without history of addiction.

Application of Sentiment Analysis and Data-Driven User Profiling in Product Iteration Design

Our study employs sentiment analysis and data-driven methodologies to construct precise user profiles and apply them to product iteration design, aiming to enhance marketing effectiveness and user satisfaction. The research data comprises 178,563 user comments and 42,786 social media posts. Sentiment features are extracted using advanced sentiment analysis algorithms such as BERT and Transformer. These features are combined with user behavior data and classified into five primary groups using the K-means clustering algorithm, each representing distinct user needs and sentiment tendencies. Based on the user profiles, three product iteration schemes were designed and implemented. The effectiveness of these iterations was validated through A/B testing, resulting in significant improvements in user satisfaction and usage rates. Regression analysis reveals that both sentiment scores and user behavior features have a significant positive impact on user satisfaction. The findings demonstrate that combining sentiment analysis with data-driven user profiling plays a crucial role in product design and marketing, offering new insights for optimizing products and enhancing competitiveness.

ExaAUAC: Arabic Twitter user age prediction corpus based on language and metadata features

Twitter is a rich resource for analyzing the contents of social media and extracting the age groups of users can be beneficial for recommender systems, marketing and advertising. Age detection task is an aspect of demographic information of users. In this study a large-scale corpus of Arabic Twitter users including 181k user profiles with diverse age groups consisting of −18, 18–24, 25–34, 35–49, 50–64, +65 is presented. The corpus is created by four methods: (1) collecting publicly available birthday announcement tweets using the Twitter Search application programming interface, (2) augmenting data, (3) fetching verified accounts, and (4) manual annotation. To have a best age detection model on the presented corpus, different evaluations are tested to find the model with highest accuracy and efficiency. Number of tweets, regression vs. classification, using metadata of users and tweets, using LSTM+CNN model vs. BERT are some parts of examinations done. Presented methodology is based on language and metadata features and final model is fine-tuned with BERT on 70k users and evaluated on 8200 manually annotated users. We show that our best model, compared with LSTM+CNN model and BERT-based similar model yields an improvement of up to 9% in F1-score and increment of 5% in accuracy, respectively. The model achieved macro-averaged F1-score of 44 on six age groups, and F1-score of 58 on three age groups of −25, 25–34, +35. The link of our proposed data is provided here: www.github.com/exaco/ExaAUAC.

Influence of Sociodemographic and Social Variables on the Relationship between Formal Years of Education and Time Spent on the Internet

This study aims to validate the impact of sociodemographic factors and differentiate the influence of social variables on the correlation between the number of years of formal education an individual has and the time they allocate to internet usage. To achieve this, we utilized a publicly available database, extracting relevant indicators for our investigation. Subsequently, we conducted analyses involving associations, regressions, and moderations among the variables under scrutiny. The results revealed statistically significant variations in daily internet usage time across different countries, residences, age groups, educational levels, and marital statuses. Factors such as living in an urban or suburban environment, being in the youth demographic, possessing a higher education, maintaining single status, having an extensive social network, holding a negative perception of health, lacking home internet access but having access at work and on the go, along with the facilitation of online communication and remote work, collectively explain the variance in daily internet usage time. The relationship between the number of years of education and the duration of internet usage is moderated by sociodemographic variables (gender, age, and marital status) as well as social variables (locations of internet usage and social contacts). These findings enable us to identify a user profile at a higher risk of developing problematic behavior in relation to internet usage, as indicated by the time invested.

User Acceptability Testing of Mobile Application in Indian Local Languages for Cardiovascular Risk Stratification and Modification among Patients with Type 2 Diabetes

Introduction: Cardiovascular disease is the leading cause of death in patients with type 2 diabetes. Digital health tools like mobile application have fast emerged as a technology capable of closing the gap in cardiovascular disease self- management and revolutionizing the way healthcare is traditionally delivered. One of the causes for low app engagement of Apps in India is perhaps that few of these apps are available in local languages. The goal is to reach as many diabetic patients as possible while avoiding linguistic hurdles.  Methodology: The ‘healthy heart’ mobile app was developed and translated into Hindi and Marathi languages for CVD risk stratification and risk management among Type 2 diabetes mellitus patients. User acceptability testing of the app on its design, presentation, content, and user- friendliness was undertaken. The feedback on utility of the app for CVD risk stratification and modification was assessed. A total 100 multilingual app users profile were noted for CVD Risk Status, Life Style Practices and CVD Risk Factors.  Results: The Healthy Heart multi-lingual app was successfully developed for CVD risk classification and risk management among Type 2 diabetes mellitus patients. The patients had the choice to select the desired language of the app from the versions available in English, Hindi and Marathi. The Mobile App's Home Screen displayed the CVD risk score and category, a health tracker to monitor compliance with WHO recommendations regarding diet, physical activity, addictions, medication adherence, diabetic, and CVD Risk Profile. The majority of respondents rated the App's design, presentation, content, and user- friendliness favorably and emphasized the utility of App for CVD self-management and risk reduction. Characteristics of Type 2 Diabetic patients demonstrated poor compliance for total fruits and vegetable intake, total fat intake and total salt intake, physical activity Guidelines apart from poor control for blood pressure, glycemic control and lipid targets.  Conclusion: The multilingual mobile App for CVD risk stratification, self-management and CVD risk reduction among diabetic patients was successfully developed in Hindi and Marathi language. User acceptability testing results were found to be favorable for the mobile app.

Dynamic analysis of a pedestrian network: The impact of solar radiation exposure on diverse user experiences

The walking experience is impacted by solar radiation exposure of pedestrian paths; this is a critical consideration for walkability assessment. The presented systematic methodology evaluates the impact of solar radiation on the user experience of pedestrian networks. Simulations were performed modelling the urban morphology in 3D and evaluating the shading provision of sidewalks at key times of the year. Three issues were investigated: the variability in solar radiation exposure of sidewalks, the difference in path length if discomfort resulting from exposure to solar radiation was prioritised over distance, and the access to shading for pedestrians of diverse walking abilities. Four user profiles were characterised by walking speed and ability to climb the stairs; adopting the perspective of diverse users provided critical information to design cities meeting the needs of vulnerable pedestrians. The resulting maps illustrated the dynamic nature of solar radiation exposure of the pedestrian network, with a critical cue on the paths chosen for optimising comfort, and the time that pedestrians would spend in the sun before finding shade. This work is a first step forward in the systematic implementation of microclimatic analysis in the walkability assessment, aimed at supporting designers in proposing solutions for ameliorating thermal stress.

New custom rating for improving recommendation system performance

Recommendation system is currently attracting the interest of many explorers. Various new businesses have surfaced with the rise of online marketing (E-Commerce) in response to Covid-19 pandemic. This phenomenon allows recommendation items through a system called Collaborative Filtering (CF), aiming to improve shopping experience of users. Typically, the effectiveness of CF relies on the precise identification of similar profile users by similarity algorithms. Traditional similarity measures are based on the user-item rating matrix. Approximately, four custom ratings (CR) were used along with a new rating formula, termed New Custom Rating (NCR), derived from the popularity of users and items in addition to the original rating. Specifically, NCR optimized recommendation system performance by using the popularity of users and items to determine new ratings value, rather than solely relying on the original rating. Additionally, the formulas improved the representativeness of the new rating values and the accuracy of similarity algorithm calculations. Consequently, the increased accuracy of recommendation system was achieved. The implementation of NCR across four CR algorithms and recommendation system using five public datasets was examined. Consequently, the experimental results showed that NCR significantly increased recommendation system accuracy, as evidenced by reductions in RMSE, MSE, and MAE as well as increasing FCP and Hit Rate. Moreover, by combining the popularity of users and items into rating calculations, NCR improved the accuracy of various recommendation system algorithms reducing RMSE, MSE, and MAE up to 62.10%, 53.62%, 65.97%, respectively, while also increasing FCP and Hit Rate up to 11.89% and 31.42%, respectively.

The Highs and Lows of Pornography Use: Does Motivation Affect Users’ Life Satisfaction?

"The negative outcomes of problematic pornography use (PPU) have been well documented, but there is a gap in the literature on the underlying mechanisms that influence the life satisfaction and mental health of pornography users. In the current study we have used a cross-sectional, person-centered approach in order to reveal the motivational and life satisfaction profile of problematic and non-problematic pornography users based on the theoretical framework of Self-determination Theory (SDT). We also wished to determine the role of self-determination in the life satisfaction of pornography users, as this variable is considered to be relevant for the life satisfaction and mental health of online pornography consumers. Our participants (N = 4302) were Hungarian speaking adults from Romania and Hungary (age M=27,91; SD=9,50), selected through sampling on social networking sites related to pornography, sexual dysfunction and addiction. Individuals were assigned to one of 3 groups (i.e., no symptoms, few symptoms, problematic use), based on the presence of symptoms related to pornography use. Demographic data was gathered, self-determination, life satisfaction and pornography use were assessed using the online version of validated instruments. Results indicated that SDT-based motivation and life satisfaction have a significant role in shaping the profile of pornography users. Participants with PPU felt less satisfied with their life, were less self-aware and experienced lower levels of perceived choice than both no symptom and few symptom groups. Although self-determination significantly predicted life satisfaction, this effect was not influenced by the problematic character of pornography use. Keywords: self-determined motives; life satisfaction; online sexual activities; problematic pornography use."

Client-side and Server-side Tracking on Meta: Effectiveness and Accuracy

Growing concern over digital privacy has led to the widespread use of tracking restriction tools, such as ad blockers, Virtual Private Networks (VPN), and privacy-focused web browsers. All major browser vendors have also deprecated, or plan to deprecate, third-party cookies to reduce tracking. Despite these efforts, advertising companies continuously innovate to overcome these restrictions. Recently, advertising platforms, like Meta, have been promoting server-side tracking solutions to bypass traditional browser-based tracking restrictions. This paper explores how server-side tracking technologies can link website visitors with their user accounts on Meta products. The goal is to assess the effectiveness and accuracy of employing this technology, as well as the effect of tracking restrictions on online tracking. Our methodology involves a series of experiments where we integrate Meta's client-side tracker (the Meta Pixel) and server-side technology (the Conversions API) on different web pages. We then drive traffic to these pages and evaluate the success rate of linking website visitors to their profiles on Meta products. Our findings show that Meta's server-side technology can match between 34% and 51% of website visitors to user profiles on Meta products using basic information like the visitor's IP address, user agent, and location data. This is comparable to Pixel-based user matching in optimal conditions (i.e., in the absence of tracking restrictions), which links between 42% and 61% of user profiles. Nevertheless, we see a considerable difference in accuracy: while the Pixel-based tracking achieves 100% accuracy, less than 65% of the profiles matched by server-side tracking are accurate.

Accelerating User Profiling in E-Commerce Using Conditional GAN Networks for Synthetic Data Generation

Abstract This paper presents the findings of a study on the profiling of online store users in terms of their likelihood of making a purchase. It also considers the possibility of implementing this solution in the short term. The paper describes the process of developing a profiling model based on data derived from monitoring user behaviour on a website. During the customer’s subsequent visits, information is collected to identify the user, record their behaviour on the page and the fact that they made a purchase. The model requires a substantial amount of training data, primarily related to the purchase of products. This represents a small percentage of total website traffic and requires a considerable amount of time to monitor user behaviour. Therefore, we investigated the possibility of using the Conditional Generative Adversarial Network (CGAN) to generate synthetic data for training the profiling model. The application of GAN would facilitate a more expedient implementation of this model on an online store website. The findings of this study may also prove beneficial to webshop owners and managers, enabling them to gain a deeper insight into their customers and align their price offers or discounts with the profile of a particular user.