IoT-aware online shopping system enhanced with gaze analysis

In online business, it is important to construct sale web pages offering attractive services for popular products in order to improve page access and purchase rates. Moreover, online shop owners are required to hold various types of sales frequently throughout the year to keep customers coming back. However, along with these web pages, management of product DB (Data Base) is required to set up complicated sales contents with high efficiency and reliability. To satisfy this requirement, a sale-oriented online-shop management support method is proposed. In this method, using a sale management web page, online-shop owners can efficiently and reliably construct attractive sale pages consistent with their DB, using hierarchical sale knowledge created by a software agent and modified by them. Namely, the automatic construction and interactive modifications of sale pages as well as the automatic/interactive update of DB for each sale product group can be done consistently and dynamically, synchronized with the sale.

User interest and behavior modeling is a critical step in online digital advertising. On the one hand, user interests directly impact their response and actions to the displayed advertisement (Ad). On the other hand, user interests can further help determine the probability of an Ad viewer becoming a buying customer. To date, existing methods for Ad click prediction, or click-through rate prediction, mainly consider representing users as a static feature set and train machine learning classifiers to predict clicks. Such approaches do not consider temporal variance and changes in user behaviors, and solely rely on given features for learning. In this paper, we propose two deep learning-based frameworks, {hbox {LSTM}}_{mathrm{cp}} and {hbox {LSTM}}_{mathrm{ip}}, for user click prediction and user interest modeling. Our goal is to accurately predict (1) the probability of a user clicking on an Ad and (2) the probability of a user clicking a specific type of Ad campaign. To achieve the goal, we collect page information displayed to the users as a temporal sequence and use long short-term memory (LSTM) network to learn features that represents user interests as latent features. Experiments and comparisons on real-world data show that, compared to existing static set-based approaches, considering sequences and temporal variance of user requests results in improvements in user Ad response prediction and campaign specific user Ad click prediction.

Nowadays, social media is quite famous for promotional media. Social media is now a business land for someone to promote and sell products, goods or services to social media users known as an online shop. The use of endorsements is one of the creative strategies in advertising that online shop sellers often use to introduce and disseminate product information that is owned widely and quickly. This research will focus on the influence of using endorsements on the sale of online shop businesses. This study examines the usefulness of endorsements to increase online shop sales for Tokikubytata. The research method used is descriptive with a qualitative data approach obtained from consumers and online shop owners through written interviews with questionnaires. The research process has several stages, starting from reading books about marketing endorsements, literature and research supporting references, understanding research backgrounds, collecting data, conducting a series of qualitative data analysis processes, and conducting written interviews and field observations. The result of this study show that endorsement is very influential in increasing the number of followers and buyers for Tokikubytata. Endorsement will help in increasing consumer confidence in the products marketed by Tokikubytata. Phenomenological studies in this study are a method used to explore that the phenomenon of endorsement can increase the number of followers for online shop.
 Keywords: endorsement, Tokikubytata, online shop

As the rapid growth of digital scientific and technical literatures, the scientific researchers need personalized retrieval to satisfy their research interests urgently. Unlike previous methods that just use simple keyword matching, we strengthen the semantic information of scientific literature by merging metadata such as title, keywords, abstract and citation in this dissertation. Then we use vector space model with tf-idf value of each term to model each scientific literature. We structure user's interest model by subject term vector with different weight. Different weight means different concern degree to each subject term by user. To emphasize the quality of recommended literature, we not only calculate the similarity between user's research interest and literatures, but also consider the total times cited of recommended literatures. As experimental dataset, we collect literatures from Web of Science under the topic of “pressure sensor”. The experimental results show that this recommendation method could well indentify user's research interest. So, it can improve efficiency of user literature retrieval and increase the accuracy of the literature recommendation.

Since the Internet of Things (IoT) will be entwined with everything we use in our daily life, the consequence of security flaws escalates. Smart objects will govern most of the home appliances and car engines yielding potential disaster scenarios. In this context, successful attacks could lead to chaos and scary scenarios (www.darkreading.com). Unprotected personal information may expose sensitive and embarrassing data to the public and attacks may threaten not only our computers and smart devices, but our intimacy and perhaps our lives too. Because persons and objects will be bonded with each other, user consent becomes critical. Therefore, thing, object, and user Identity will be the focus of future IoT security solutions, yielding a Trust, Security, and Privacy (TSP) paradigm, which may constitute the Achilles' heel of IoT. While security issues are quite straightforward, mainly from background knowledge, privacy issues are far more complex. Privacy constitutes a rather challenging task, even for the m...

Analyzing the eye gaze to estimate the text understanding is a good way to overcome the drawbacks of classic question based assessment tests. In particular it does not suffer from random answers, question misunderstanding and can cover every parts of the text. In this paper we propose a method to estimate the objective understanding of a learner by analyzing his eye movements while reading. We conduct our experiment on Japanese texts and try to predict, by analyzing the eye gaze, how many questions about the texts the reader will be able to answer to. We show that we obtain 5.27% of error in the number of correct answers estimation by using eye gaze features. As a comparison, we try to predict the number of correct answers by using the reader's self assessment understanding and show that it leads to 9.04% error.

Shoulder surfing attacks (SSAs) are a type of observation attack designed to illicitly gather sensitive data from "over the shoulder" of victims. This attack can be directed at mobile devices, desktop screens, Personal Identification Number (PIN) pads at an Automated Teller Machine (ATM), or written text. Existing solutions are generally focused on authentication techniques (e.g., logins) and are limited to specific attack scenarios (e.g., mobile devices or PIN Pads). We present ShotjldAR, a mobile and usable system to detect SSAs using multimodal eye gaze information (i.e., from both the potential attacker and victim). ShouldAR uses an augmented reality headset as a platform to incorporate user eye gaze tracking, rear-facing image collection and eye gaze analysis, and user notification of potential attacks. In a 24-participant study, we show that the prototype is capable of detecting 87.28% of SSAs against both physical and digital targets, a two-fold improvement on the baseline solution using a rear-facing mirror, a widely used solution to the SSA problem. The ShouldAR approach provides an AR-based, active SSA defense that applies to both digital and physical information entry in sensitive environments.

The growing use of digital marketing has heightened concerns about privacy, particularly regarding the disclosure of personal data during online transactions. In online shopping, consumers are often required to provide personal information to access services offered by digital companies. At the same time, they worry that their data may be used by third parties for unrelated purposes without their consent. This behaviour reflects the so‑called privacy paradox, in which consumers express strong privacy concerns yet continue to share personal data in exchange for perceived benefits. This study, therefore, examines how consumers’ willingness to disclose (WTD) sensitive personal information when using online travel agencies (OTAs) is influenced by sociodemographic and psychological factors associated with the privacy paradox. To address this objective, both qualitative and quantitative data were used. Qualitative data were gathered through in‑depth interviews and focus groups. Participants for the interviews were recruited using a snowball sampling technique, while focus group participants were selected through an open recruitment process. Insights from these qualitative activities revealed that online booking decisions are shaped by several factors, including consumer ambivalence, trust, demographic characteristics, and concerns about the lack of transparency in personal data usage. Qualitative data were analysed using NVivo software. Findings from the qualitative phase informed the development of a contingent valuation survey administered in Indonesia and the UK to 493 and 489 participants, respectively. The survey included questions designed to assess how respondents’ sociodemographic characteristics, habits, online privacy literacy, concerns, and psychological factors—such as trust, perceived risks and benefits, and ambivalence—influence their willingness to disclose sensitive data when booking travel online. For respondents willing to disclose personal information, a contingent valuation scenario was used to estimate the price at which they were willing to pay (WTP) or willing to accept (WTA) compensation for releasing health‑related information. WTP and WTA values were elicited using the payment card and double‑bounded dichotomous choice techniques, respectively. WTD was estimated using 28 logistic regression, while WTP and WTA were analysed using Tobit and interval regression models. Results indicate that age and benefit–risk assessment positively influence WTD, whereas privacy concerns negatively affect it. Habits, expenditure, and booking frequency positively influence WTP. Education level and trust increase WTA, while age and technical familiarity reduce WTA. Cross‑cultural comparisons show that UK consumers exhibit stronger privacy concerns and higher WTP to protect personal data, whereas Indonesian consumers are more likely to accept discounts in exchange for data sharing, influenced by contextual trust and economic considerations. Overall, the findings highlight the importance of transparent data practices, enhanced consumer education, and trust‑building initiatives in e‑commerce. This study contributes to a deeper understanding of consumer privacy concerns and decision‑making in the digital economy, emphasising the complexities underlying online behaviour. Implications for marketers, policymakers, and online businesses are discussed, with a focus on strengthening privacy protection and fostering consumer trust to support sustainable e‑commerce growth. Future research should examine longitudinal behavioural patterns and the impact of emerging technologies on data‑sharing preferences across cultures.

In the era of digitization, online digital advertising is one of the best techniques for modern marketing. This makes advertisers rely heavily on accurate user interest and behavior modelling to deliver precise advertisement impressions and increase click-through rates. The classic approach to model user interests has often required the use of predefined feature sets which are typically stagnant and not representative of temporal changes and trends in user behavior. While recent advances in deep learning offer potential solutions to these obstacles, many existing approaches fail to address the sequential nature of user interactions. In this paper, we propose an optimized Bi-Directional Long Short-Term Memory (Bi-LSTM) based user interest modeling approach together with an Updated version of Parrot Optimizer (UPO) to enhance performance. It treats the user activity as a temporal sequence which well fits the changing nature of user interest and preferences over time. The proposed approach is evaluated on two important tasks: predicting the probability that a user will click on an ad and predicting the probability that a user will click on a particular type of ad campaign. Simulation results demonstrate that the proposed method provides superior results than the static set-based approaches and achieves significant improvements on both user ad responses predictions and user ad clicks at the campaign level. The research also enhances the efficiency of user interest modeling with significant implications for online advertising, recommendation systems, and personalized marketing.

It is our great pleasure to welcome you to the 7th Workshop on Eye Gaze in Intelligent Human Machine Interaction -- Gaze-in 2014. Eye gaze is one of the most important aspects in understanding and modeling human-human communication, and it has great potential also in improving humanmachine and robot interaction. In human face-to-face communication, eye gaze plays an important role in floor and turn management, grounding, and engagement in conversation. In human-computer interaction research, social gaze, gaze directed at an interaction partner, has been a subject of increased attention. In the previous workshops we have discussed a wide range of issues for eye gaze involved in multimodal human-machine/robot/agent interaction; technologies for sensing human attentional behaviors, attentional behaviors in problem-solving and task-performing, multimodal communication, interpretation and generation. In addition to these topics, this workshop also focuses on eye gaze in multiparty interaction and real-world applications, especially on mobile platforms where remarkable progress has been achieved in recent years. This year's workshop continues in these lines and explore the growing area of gaze in intelligent interaction research by bringing together researchers from domains of human sensing, multimodal processing, humanoid interfaces, intelligent user interfaces, and communication science. The participants exchange ideas to develop and improve methodologies for this research area with the long-term goal of establishing a strong interdisciplinary research community in "attention aware interactive systems." The call for papers attracted eight submissions from Germany, Turkey, Japan, the United Kingdom, Poland, and the United States. These papers covers the following research topics: eye tracking in security and medical applications, eye gaze behavior analysis in grouped face-to-face communication and collaborative learning, and cognitive function in investigating musical sense and the conversation with virtual agents on mobile devices. Most of the papers were reviewed by three reviewers with some exceptions where there were only two reviewers. Gaze-in 2014 also featured a keynote talk by Dan Bohus (Microsoft Research, USA) titled: "Attention and Gaze in Situated Language Interaction."

The era of the digital economy as it is today has demanded business people to carry out their business activities online. As a result, buyers will also make purchases online. It has implications for business competition. In this case, Law (UU) No. 5 of 1999 concerning the Prohibition of Monopolistic Practices and Unfair business Competition has not accommodated the impact of the digital economy. So with that, this research has two objectives. The objectives are; First, to know the effect of the digital ecosystem on business competition law in Indonesia. Second, to see the role of the Business Competition Supervisory Commission (KPPU) in the digital economy era in the event of unfair business competition. This research uses the type of juridical-normative research. The impact of the digital economy on business competition in Indonesia has resulted in a lot of abuse of the digital platform market. In this case, digital platforms are increasing with vertical business development. This business development increases the ability of digital platforms to collect more data, increase their competitiveness and become online shop owners and application users, so that the dominant position of digital platforms can be abused, for example, discriminating against competitors in retail, exclusivity agreements with consumers, and selling policies. With losses may result in competitors becoming uncompetitive in the market and leaving the market. Responding to these challenges, it is necessary to have a regulation that regulates in a more specific scope. This is because several countries in Europe have revised their business competition law regulations to protect business actors. In addition, as a form of responding to the challenges of the times that have changed the direction of the economy and online business. Of course, the government and business actors must work together to achieve good goals for the parties who will have an impact.

Many researchers and companies have engaged in estimating users’ interests so that an online shopping system can tell what he/she wants now. This paper tackles the next challenge in online i.e., predicting the times that users go shopping online. To predict the timing of online we focus on in web activities and propose a search wandering score (SWS). Online shopping behavior can be categorized into three states: shop-ping, shopping, and others. Wandering shopping is a state in which users make purchases in high SWS situations; focused shopping is a state in which users buy things in low SWS situations. Unlike previous studies, our work is based on an analysis of large-scale data containing shopping and logs produced by approximately 200,000 users of a real web portal site for over a year. The results of an extensive evaluation show that our methodology can predict user’s future shopping behavior types with 86% accuracy. This research is the first step towards understanding the relationship between users’ mental states and their online shopping behavior.

Willingness to disclose (WTD) personal information in online shopping is relatively low, though people willingly disclose a lot of information about themselves in social networking. The contradiction between personal data disclosure in the two types of online interactions is a research gap that is hardly explainable within the most used theoretical bases. Another research gap is in balancing up roles of dispositional and situational antecedents of data disclosure. The third research gap is in the role of perceptions about legal regulatory systems on WTD. These gaps required to look for a new theoretical grounding of willingness to disclose personal data. The three research gaps have been addressed on the basis of Social Exchange Theory (SET), which has been rarely considered in marketing studies, and in analysis of personal data disclosure. SET sees interactions (including exchange of personal data for certain benefits) as social exchanges of two types of exchanges (negotiated and reciprocal). Additionally, SET enables to consider perceptions of benefits of exchange, characteristics of exchange participants as well as their relative power, which is important in interactions between individuals and companies/online stores. All the above-mentioned considerations in regards to the applicability of SET for grounding of WTD personal data has been conceptualized and empirically tested in three subsequent studies. The first study aimed to test whether the SET is applicable for the modelling of willingness to disclose personal data in online shopping, considering the possible interaction between the two types of social exchange: reciprocal and negotiated. The study included antecedents of trust-distrust continuum and two mediators: perceived regulatory effectiveness and perceived lack of control. The second study included perceived benefits of data disclosure (experienced earlier and expected), store trust and perception of relative power. The third study concentrated on the most important situational predictor of WTD personal data – store trust – and assessed its antecedents, including the presence of online only versus online and offline channels. The studies confirmed suitability of SET for the modelling of WTD, showed the linkage between reciprocal and negotiated exchange and the importance of the factor of trust in a store.

With the growth of the internet, electronic (online) business has become an important trend in the economy. This study investigates how retailers could enhance their shopping processes and hence help sustain their e-business development. Therefore, we propose a unified information system-consumer behavior (IS-CB) model for online shopping to analyze factors that impact online shopping. We used an online survey to gather data from 633 online customers to test the theoretical model, matching differences using structural equation modeling. Highly influencing factors for the IS-CB online shopping model included perceived value (PV), perceived risk (PR), social factors (SF), perceived ease of use (PEOU), perceived usefulness (PU), online shopping intention, trust, online shopping experience, actual online shopping purchases, entertainment gratification (EG), website irritation (WI), information design (ID), visual design (VD), and navigation design (ND). This study provides important theoretical and practical implications. PV and trust in online shopping can nurture positive attitudes and shopping intentions among online customers. Well-designed websites produce higher levels of trust and reduced WI. Similarly, online shopping sites with better ID, ND, and VD also reduce WI and increase trust. This study fills gaps in previous studies relating to IS and CB and provides explanations for IS and CB constituent impacts on acceptance and use of online shopping. The proposed unified IS-CB explains consumer online shopping patterns for a sustainable e-business.

Internet of Things (IOT) is an extension and expansion of the internet development. The ultimate goal of IOT system is to realize the exchange and communication between human and thing as well as thing to thing. With the constant development of IOT, the intellectual degree of the future IOT would be higher and higher, the application filed would be getting extensive too. IOT plays a very important promoting effect on the logistic service system, corporation production and operation management, the production quality control of the online shopping by consumers and other aspects of the electronic commerce. IOT E-commerce provides extreme convenience to people’s work and life, but its information safety still has some restriction. The character of Analytic Hierarchy Process (AHP) is to divide the complicated problem into simple combinations of multiple hierarchies and factors, and group each factor in two for comparison and calculation, according to the calculated result to make judgment and make choice. This article, based on AHP model, establishes information security evaluation model of IOT electronic commerce, evaluates on the five physical measures to protect electronic label by theory analysis on algorithm and AHP model, which has certain referential value to the IOT E-commerce information security evaluation work.