Product Recommendation Agents Research Articles

Digital nudges to stimulate healthy and pro-environmental food choices in E-groceries

In response to the detrimental health- and environmental impacts of European consumers' dietary patterns, Nutri-Scores and Eco-Scores have been introduced on packages as guidance for choices. Whereas the scores are promising to improve food choices from a nutritional point of view, the scant available literature suggests very limited effects on the environmental impact of food choices. Therefore, there remains a need to explore ways to bring about improvements in both areas. As a growing share of consumers buys food groceries online, new opportunities to steer food choices are being created. This article explores the potential of several digital functionalities to further stimulate healthier and pro-environmental food choices amongst consumers. These functionalities included product recommendation agents, product scores, a real-time average impact score of the chosen food basket and a personalised social norm. Those were tested in a two-stage randomized controlled trial with 1000 Belgian household food decision makers in a mock-up E-grocery. Indices reflecting the nutritional quality (NQI) and environmental impact (EII) of the selected food baskets were calculated. The results indicate that at first, displaying a combined Nutri- and Eco-Score at product level led to improved NQI's, but not EII's. However, the scores also led to shifting behaviour in EII's when facilitated with recommendation agents. The display of the average impact scores of the selected basket and of social norms did not lead to additional improvements. Hence, a combined Nutri- and Eco-Score labelling system is recommended, but an enabling environment to consider both scores is important to realise a shift towards more healthy and environmentally friendly food choices. Apart from manifesting healthier and environmentally friendly products with a centralised labelling system, improving their accessibility should be considered at least as important for behavioural changes.

Scratch my back and I'll scratch yours: The impact of user effort and recommendation agent effort on perceived recommendation agent quality

Product recommendation agents (RAs) assist online firms to adapt their suggested offers to users’ preferences, thereby lowering users’ decision effort. The concept of effort is central in decision-making, yet it remains unclear whether it should be regarded as a cost or as a benefit improving the odds of a better decision. Building on Social Exchange theory, we suggest that interactions between users and RAs are driven by the concepts of perceived interdependence and reciprocity. We suggest that perceived user effort decreases the perceived RA quality, whereas RA effort increases the perceived RA quality. We conducted two experimental studies across different contexts. We found that users evaluate RAs based on their own expended effort, in relation to how much effort they perceived the RA has put into the process of generating recommendations. Such an effect is attenuated by users’ familiarity with the product context. Our findings offer important insights into how online firms can improve the use of their RAs.

Effects of Sponsorship Disclosure on Perceived Integrity of Biased Recommendation Agents: Psychological Contract Violation and Knowledge-Based Trust Perspectives

Product recommendation agents (RAs) are widely employed by online merchants to facilitate consumers’ decision making. Users’ perceived integrity of these RAs becomes a critical trust concern when RAs apply sponsorship practices and recommend products biased toward sponsored products. Sponsorship disclosure is enforced by the U.S. Federal Trade Commission, but many technologies fail to comply probably because of their concerns on users’ trust in the biased technologies. This research investigate when sponsorship disclosure is most effective in enhancing users’ perceived RA integrity. A laboratory experiment revealed two major findings related to the benefits of sponsorship disclosure in enhancing users’ perceived integrity of a biased RA. First, for users with high prior knowledge about the prevalence of sponsorships used by RAs in general, sponsorship disclosure can reduce users’ perceived psychological contract violations of a biased RA and then increase users’ perceived RA integrity. For users with limited such prior knowledge, the disclosure fails to reduce these perceived violations. Second, regardless of the level of such prior knowledge of users, sponsorship disclosure enhances users’ perceived transparency of a biased RA, which, in turn, leads to perceived RA integrity.

Scratch My Back and I’ll Scratch Yours: The Impact of the Interaction Between User Effort and Recommendation Agent Effort on Perceived Recommendation Agent Quality

Product recommendation agents (RAs) assist online firms to adapt their suggested offers to users’ preferences, there by lowering consumers’ decision effort and improving their decision accuracy. The abundance of product choices available on the internet has made the need for RAs essential mainly due to the increased decision effort by consumers associated with making a selection. The concept of effort has been central in decision-making, yet evidence on the role of effort has been contradictory on whether it should be regarded merely as a cost for the user or as a benefit as well since higher effort improves the odds of a better decision. Building on Social Exchange theory, we suggest that interactions between users and RAs are driven by the concepts of perceived interdependence and reciprocity. We suggest that perceived user effort decreases, whereas RA effort increases, perceived RA quality. We further posit that users evaluate RAs based on their own individual effort expended in relation to their perceptions of the effort that the RA has put into the process of generating recommendations. The evidence from two experimental studies and an integrative data analysis suggests that the negative effect of user effort on RA quality is reduced when users perceive greater RA effort. Such an effect is negatively moderated by user familiarity. Our findings enrich the understanding of the conflicting role of user effort in decision-making and offer important insights into how online firms can improve the utilization of their RAs.

An empirical examination of the influence of biased personalized product recommendations on consumers' decision making outcomes

To assist consumers in product search and selection while shopping online, many e-commerce retailers have implemented web-based product recommendation agents (PRAs). However, consumers are empowered to the extent that the PRAs provide true personalization by recommending products based solely on, and thus best representing, consumers' preferences. This study constructs and empirically tests a theoretical model that examines how biased recommendations from PRAs influence consumers' decision quality and decision effort. The results of an online experiment show that consumers are extremely vulnerable to biased personalized recommendations from online PRAs. In addition, our results extend prior research by identifying perceived personalization as a critical mechanism driving the influence of biased PRA on consumers' decision quality and decision effort. This study fills a void in the literature and calls attention to an insidious form of manipulation made possible by innovative technologies supporting e-commerce.

Effects of rational and social appeals of online recommendation agents on cognition- and affect-based trust

Online product recommendation agents (RAs) utilize rational and social appeals to enhance their persuasive power. However, the underlying mechanisms of how these various appeals work are still not clear. In this study, a laboratory experiment was conducted to examine the differential effects of explanation facilities and avatar interfaces as instances of rational and social appeals, respectively. We investigated (1) the effects of these appeals on cognition- and affect-based trust, and (2) the distinct persuasive outcomes of cognition- and affect-based trust.The results show that explanation facilities significantly enhance users' cognition-based trust. Meanwhile, avatar interfaces have a significant positive impact on users' affect-based trust, but only for those who rate the avatar as highly professional. Besides, our findings attest to the fact that cognition-based trust mainly delivers the utilitarian value (perceived usefulness), while affect-based trust mainly contribute to the hedonic value (perceived enjoyment) of using a RA.

Designing Warning Messages for Detecting Biased Online Product Recommendations: An Empirical Investigation

The increasing adoption of product recommendation agents (PRAs) by e-commerce merchants makes it an important area of study for information systems researchers. PRAs are a type of Web personalization technology that provides individual consumers with product recommendations based on their product-related needs and preferences expressed explicitly or implicitly. Whereas extant research mainly assumes that such recommendation technologies are designed to benefit consumers and focuses on the positive impact of PRAs on consumers’ decision quality and decision effort, this study represents an early effort to examine PRAs that are designed to produce their recommendations on the basis of benefiting e-commerce merchants (rather than benefiting consumers) and to investigate how the availability and the design of warning messages (a potential detection support mechanism) can enhance consumers’ performance in detecting such biased PRAs. Drawing on signal detection theory, the literature on warning messages, and the literature on message framing, we identified two content design characteristics of warning messages—the inclusion of risk-handling advice and the framing of risk-handling advice—and investigated how they influence consumers’ detection performance. The results of an online experiment reveal that a simple warning message without accompanying advice on how to detect bias is a double-edged sword, because it increases correct detection of biased PRAs (hits) at the cost of increased incorrect detection (false alarms). By contrast, including in warning messages risk-handling advice about how to check for bias (particularly when the advice is framed to emphasize the loss from not following the advice) increases correct detection and, more importantly, also decreases incorrect detection. The patterns of findings are in line with the predictions of signal detection theory. With an enriched understanding of how the availability and the content design of warning messages can assist consumers in the context of PRA-assisted online shopping, the results of this study serve as a basis for future theoretical development and yield valuable insights that can guide practice and the design of effective warning messages.

Consumer participation in online product recommendation services: augmenting the technology acceptance model

Purpose – This paper aims to examine the complex role of consumer participation by empirically testing a theoretical model within the online context of consumer using product recommendation agents (RAs) that integrates consumer participation into the technology acceptance model (TAM). Recent research starts questioning whether consumer participation is a double-edged sword, although its positive effects have been widely documented in the services marketing literature. Design/methodology/approach – Data were collected from 243 respondents comprising both genders with varied age groups, education levels, household income and ethnicities. Participants interacted with an existing RA, searching product information for a simulated purchase involving either high or low financial risk. Confirmatory factor analysis (CFA) and Structural equations modeling (SEM) were used for assessing construct validity and testing hypotheses, respectively. Findings – Consumer participation was found to positively affect enjoyment but negatively affect perceived ease of use of an RA, which was exacerbated when the purchase was of high financial risk. Predictions based on TAM were all supported in this study. Research limitations/implications – This research evidenced consumer participation’s dual-effect and identified financial risk as a moderator of consumer participation’ negative effect. Future research could employ a different design such as using controlled lab settings and conducting longitudinal studies to replicate the study. Practical implications – Findings from this research provide guidance to RA design regarding the amount of consumer participation, consumer perceptions of RA use (ease of use, usefulness and enjoyment) and financial risk involved in the purchase. Originality/value – This research sheds new light on the role of consumer participation through uncovering its dual-effect, thus complementing the services marketing and RA literature.

Cue consistency and page value perception: Implications for web-based catalog design

The web-based product catalog is a central element of online retailing. Although the extant research has studied the effect of design elements, such as product presentation, recommendation agents, and image and text on consumer choice, little is known about how Internet vendors could distribute products in a multi-page online product catalog for better performance. It is well-known that the first page of an online product catalog is particularly important to a vendor. Based on price signaling literature and cue consistency theory, this study investigates how price and product popularity cues could be carefully designed for the first page to achieve better sale performance. This study suggests there is a delicate balance point where price cues and popularity cues can achieve consistency and synergy and lead to better page value perceptions for the first page. The boosted page value perceptions, in turn, lead to better sales from the first page. This study extends the theory of cue consistency to the product group level.

Consumer participation in using online recommendation agents: effects on satisfaction, trust, and purchase intentions

Online product recommendation agents (RAs) are gaining greater strategic importance as a critical touch-point between marketers and consumers. Yet, the role of consumer participation in using RAs has not been examined. This study shows that greater consumer participation in using an RA leads to more satisfaction, greater trust, and higher purchase intentions, related to the RA and its recommendations. In contrast, the financial risk (associated with the product under consideration) reduces satisfaction, trust, and purchase intentions, and it also moderates the effect of consumer participation on these same variables. The findings extend the literature and suggest actionable implications for marketing strategy.

Research Note—The Influence of Trade-off Difficulty Caused by Preference Elicitation Methods on User Acceptance of Recommendation Agents Across Loss and Gain Conditions

Prior studies on product recommendation agents (RAs) have been based on the effort-accuracy perspective in which the amount of effort required to make a decision and the accuracy of such decisions are two dominant antecedents of user acceptance of RAs. The current study extends the effort-accuracy perspective by considering trade-off difficulty, a type of negative emotion that arises when attainment of one's goals is blocked by the attainment of other goals; consequently, one must make trade-offs among the conflicting goals. Many product purchase choices for which RAs are used require users to make trade-offs among conflicting product attributes. A key feature of RAs, the preference elicitation method (PEM), often compels users to make explicit trade-offs. We examine whether an RA's PEM generates trade-off difficulty, which, in turn, affects users' evaluations (i.e., perceived amount of effort and perceived accuracy of recommendations) and the resultant acceptance of the RA. Trade-off difficulty influences users' evaluations of an RA via perceived control over execution of the RA PEM. In addition, the decision context in which users employ a PEM moderates the degree to which that PEM generates trade-off difficulty. Specifically, a PEM generates a greater degree of trade-off difficulty in a choice context that leads to a loss than in a choice context that leads to a gain. Consequently, users exert more effort to cope with trade-off difficulty in a loss condition. Because users voluntarily spend more effort, the negative influence of perceived effort on users' acceptance of an RA—which is supported in prior studies—decreases in a loss condition. A laboratory experiment was conducted using two between-subject factors: two RAs, one that employed a trade-off-compelling PEM and the other a trade-off-hiding PEM, and two decision contexts, one of which was a loss condition and the other a gain condition. The results supported all of the hypotheses.

Usage and success factors of commercial recommendation agents

PurposeSince their inception, which took place more than two decades ago, product recommendation agents (RAs) still attract very few consumers. Notably, most of academic work in the field had an empirical quantitative structure. In addition, no research has developed a comprehensive model to explain the adoption and usage of commercial RAs. The purpose of this paper is to follow a qualitative approach to investigate the factors behind the adoption and usage of commercial RAs, explore the effect of user age, and deduce the success factors of these RAs.Design/methodology/approachThis research followed a qualitative approach. Qualitative research aims to form an in‐depth understanding of human behavior. It is essential for building grounded theory and for proposing comprehensive models for future examination. As such, in four discussion groups, participants provided their input following the shopping trial for a product using a factual RA (MyProductAdvisor.com). Discussion groups were used because they outline an important aspect of qualitative research and because they are ideal for both the inception and development of products and services.FindingsUnderlying the major themes, the analysis first provides insight in consumers' RA use and the products consumers regard as adequate to be offered using a commercial RA. The analysis then delineates some important factors that can be considered by developers to enhance the usability and trustworthiness of commercial RAs. Further, the analysis suggested four higher‐order factors that can be considered the success factors of a commercial RA: users appear to require a commercial RA that is friendly, smart, trusted, and informational. The themes that emerged from participants in the youth and the older discussion groups were rather invariant.Originality/valueThis is one of the few qualitative studies that focused on commercial RAs. The commercial RA success factors and their determinants are summarized in the form of a general framework to guide future work. This qualitative work provides a cornerstone that is of importance to theory development in the field of intelligent RAs and assistive technology. The results have important implications for RAs' developers and researchers.

Interaction design for mobile product recommendation agents

Mobile product recommendation agents (RAs) are software systems that operate on mobile handheld devices, using wireless Internet to support users' decisions en route, such as consumers' product choices in retail stores. As the demand for ubiquitous access to the web grows, potential benefits of mobile RAs have been recognized, albeit with little supporting empirical evidence. We investigate whether and how mobile RAs enhance users' decisions in retail stores by reducing the effort to make purchase decisions while augmenting the accuracy of the decisions. In addition, to identify potential design principles for mobile RAs, we compare and evaluate two interaction styles of mobile RAs: alternative-driven (RA-AL) versus attribute-driven (RA-AT) interactions. The results of a laboratory experiment conducted in a simulated store indicate that mobile RAs reduced users' perceived effort and increased accuracy of their decisions. Furthermore, RA-AL users made more accurate decisions than RA-AT users due to the RA-AL's interaction style, which was compatible with the way in which users processed information and made decisions in the store. These empirical results support the notion that mobile RAs should be designed to fit the user's task undertaken in the particular context.

A study of demographic embodiments of product recommendation agents in electronic commerce

Product Recommendation Agents (PRAs) and other web-based decision aids are deployed extensively to provide online shoppers with virtual advising services. While the design of PRA’s functional features has received a high degree of attention in academic studies, the social aspects of human–PRA interactions are comparatively less explored. This paper investigates the potential of enhancing users’ social experiences of interacting with an anthropomorphic PRA (i.e., an agent with human-like characteristics, such as facial expressions, body gestures, or speech output) by manipulating its demographic embodiments. The two demographic variables assessed are ethnicity and gender. As suggested by similarity-attraction theory and social identity theory, the results of our laboratory experiment reveal that PRAs that match the ethnicity, though not the gender, of their users are perceived as more sociable, more enjoyable, and more useful to interact with than the mismatched ones. More interestingly, the “matching-up” effects of ethnicity are more significant among female users than males. Implications for practitioners on how to use an anthropomorphic agent’s demographic characteristics to enhance users’ interaction experience are also discussed.

E-commerce product recommendation agents

Recommendation agents (RAs) are software agents that elicit the interests or preferences of individual consumers for products, either explicitly or implicitly, and make recommendations accordingly....

E-Commerce Product Recommendation Agents: Use, Characteristics, and Impact

Recommendation agents (RAs) are software agents that elicit the interests or preferences of individual consumers for products, either explicitly or implicitly, and make recommendations accordingly. RAs have the potential to support and improve the quality of the decisions consumers make when searching for and selecting products online. They can reduce the information overload facing consumers, as well as the complexity of online searches. Prior research on RAs has focused mostly on developing and evaluating different underlying algorithms that generate recommendations. This paper instead identifies other important aspects of RAs, namely RA use, RA characteristics, provider credi'r, and user-RA interaction, which influence users' decision-making processes and outcomes, as well as their evaluation of RAs. It goes beyond generalized models, such as TAM, and identifies the RA-specific features, such as RA input, process, and output design characteristics, that affect users' evaluations, including their assessments of the usefulness and ease-of-use of RA applications. Based on a review of existing literature on e-commerce RAs, this paper develops a conceptual model with 28 propositions derived from five theoretical perspectives. The propositions help answer the two research questions: (1) How do RA use, RA characteristics, and other factors influence consumer decision making processes and outcomes? (2) How do RA use, RA characteristics, and other factors influence users' evaluations of RAs? By identifying the critical gaps between what we know and what we need to know, this paper identifies potential areas of future research for scholars. It also provides advice to information systems practitioners concerning the effective design and development of RAs.

Trust In and Adoption of Online Recommendation Agents

Online product recommendation agents are becoming increasingly prevalent on a wide range of websites. These agents assist customers in reducing information overload, providing advice to find suitable products, and facilitating online decision-making. Consumer trust in recommendation agents is an integral factor influencing their successful adoption. However, the nature of trust in technological artifacts is still an under-investigated and not well understood topic. Online recommendation agents work on behalf of individual users (principals) by reflecting their specific needs and preferences. Trust issues associated with online recommendation agents are complicated. Users may be concerned about the competence of an agent to satisfy their needs as well as its integrity and benevolence in regard to acting on their behalf rather than on behalf of a web merchant or a manufacture. This study extends the interpersonal trust construct to trust in online recommendation agents and examines the nomological validity of trust in agents by testing an integrated Trust-TAM (Technology Acceptance Model). The results from a laboratory experiment confirm the nomological validity of trust in online recommendation agents. Consumers treat online recommendation agents as “social actors” and perceive human characteristics (e.g., benevolence and integrity) in computerized agents. Furthermore, the results confirm the validity of Trust-TAM to explain online recommendation acceptance and reveal the relative importance of consumers’ initial trust vis-a-vis other antecedents addressed by

"Double Agents": Assessing the Role of Electronic Product Recommendation Systems

Electronic information can easily overwhelm people. Software tools have been introduced to assist humans in filtering and organizing information into more digestible amounts and formats. Many of these tools are altruistic in the sense that they have no vested interest in what the user does with the information. However, some are designed not only to assist buyers but also to steer them in a particular direction. This makes them double agents. Examples of such decision aids exist at a number of vendor sites and include Amazon.com's Your Store, GMs Auto Choice Advisor and IBMs Solution Profiler. This article reviews the research on electronic recommendation agents. It focuses on tools that provide online shoppers with personalized product recommendations and explores the benefits and potential difficulties consumers may experience when using such tools. The article concludes that having a consumer-centric double-agent perspective can lead to a deeper and more comprehensive understanding of the interaction between electronic product-recommendation agents and consumers. This, in turn, can spur the design of better and more effective recommendation tools that allow consumers to speed up their decision processes and improve the quality of the choices they make.

Eliciting Online Customers’ Preferences: Conjoint vs Self-Explicated Attribute-Level Measurements

The growth of the Internet for shopping has led to an increasing interest in tools for assisting consumers with decision-making, efficienfly using the vast quantity of widely dispersed information. Online product recommendation agents gather information from consumers and then match these consumer preferences with their database of products to recommend the best product. Two approaches can be taken for gathering information from consumers on their preferences – conjoint-type full-profile ratings or self-explicated ratings. That is, organizations may infer consumers’ preferences for attributes and levels on the basis of their ratings of several alternative products or may simply directly ask them their evaluations of various attributes and levels. We compare these two approaches and find that, in general, they do not result in the same conclusions. In this paper we examine the differences in the approaches to making recommendations and discuss the implications of these differences. Our results show that there is a closer match between the methods for products closer to the extremes of consumer preference. Also, our study shows that a recommendation agent should offer more than one recommendation in order to match the needs of the system user.