Search results

The purpose of this paper is to explore the effects of online recommender systems (RS) on three types of diversity: algorithmic recommendation diversity, perceived recommendation diversity and sales diversity. The analysis distinguishes different recommendation algorithms and shows whether user perceptions match the actual effects of RS on sales.

An online experiment was conducted using a realistic shop design, various recommendation algorithms and a representative consumer sample to ensure the generalizability of the findings.

Recommendation algorithms show a differential impact on sales diversity, but only collaborative filtering can lead to higher sales diversity. However, some of these effects are subject to how much information firms have about users’ preferences. The level of recommendation diversity perceived by users does not always reflect the factual diversity effects.

Recommendation and consumption patterns might differ for other types of products; future studies should replicate the study with search or credence goods. The authors also recommend that future research should move from taking a unidimensional measure for the assessment of diversity and employ multidimensional measures instead.

Online shops need to conduct a more comprehensive assessment of their RS’ effect on diversity, taking into account not only the effects on their sales distribution, but also on users’ perceptions and faith in the recommendation algorithm.

This study offers a framework for assessing different forms of diversity in online RS. It employs various recommendation algorithms and compares their impact using not just one but three different types of diversity measures. This helps explaining some of the contradictious findings from the previous literature.

Improving the performance of recommender systems (RSs) has always been a major challenge in the area of e-commerce because the systems face issues such as cold start, sparsity, scalability and interest drift that affect their performance. Despite the efforts made to solve these problems, there is still no RS that can solve or reduce all the problems simultaneously. Therefore, the purpose of this study is to provide an effective and comprehensive RS to solve or reduce all of the above issues, which uses a combination of basic customer information as well as big data techniques.

The most important steps in the proposed RS are: (1) collecting demographic and behavioral data of customers from an e-clothing store; (2) assessing customer personality traits; (3) creating a new user-item matrix based on customer/user interest; (4) calculating the similarity between customers with efficient k-nearest neighbor (EKNN) algorithm based on locality-sensitive hashing (LSH) approach and (5) defining a new similarity function based on a combination of personality traits, demographic characteristics and time-based purchasing behavior that are the key incentives for customers' purchases.

The proposed method was compared with different baselines (matrix factorization and ensemble). The results showed that the proposed method in terms of all evaluation measures led to a significant improvement in traditional collaborative filtering (CF) performance, and with a significant difference (more than 40%), performed better than all baselines. According to the results, we find that our proposed method, which uses a combination of personality information and demographics, as well as tracking the recent interests and needs of the customer with the LSH approach, helps to improve the effectiveness of the recommendations more than the baselines. This is due to the fact that this method, which uses the above information in conjunction with the LSH technique, is more effective and more accurate in solving problems of cold start, scalability, sparsity and interest drift.

The research data were limited to only one e-clothing store.

In order to achieve an accurate and real-time RS in e-commerce, it is essential to use a combination of customer information with efficient techniques. In this regard, according to the results of the research, the use of personality traits and demographic characteristics lead to a more accurate knowledge of customers' interests and thus better identification of similar customers. Therefore, this information should be considered as a solution to reduce the problems of cold start and sparsity. Also, a better judgment can be made about customers' interests by considering their recent purchases; therefore, in order to solve the problems of interest drifts, different weights should be assigned to purchases and launch time of products/items at different times (the more recent, the more weight). Finally, the LSH technique is used to increase the RS scalability in e-commerce. In total, a combination of personality traits, demographics and customer purchasing behavior over time with the LSH technique should be used to achieve an ideal RS. Using the RS proposed in this research, it is possible to create a comfortable and enjoyable shopping experience for customers by providing real-time recommendations that match customers' preferences and can result in an increase in the profitability of e-shops.

In this study, by considering a combination of personality traits, demographic characteristics and time-based purchasing behavior of customers along with the LSH technique, we were able for the first time to simultaneously solve the basic problems of CF, namely cold start, scalability, sparsity and interest drift, which led to a decrease in significant errors of recommendations and an increase in the accuracy of CF. The average errors of the recommendations provided to users based on the proposed model is only about 13%, and the accuracy and compliance of these recommendations with the interests of customers is about 92%. In addition, a 40% difference between the accuracy of the proposed method and the traditional CF method has been observed. This level of accuracy in RSs is very significant and special, which is certainly welcomed by e-business owners. This is also a new scientific finding that is very useful for programmers, users and researchers. In general, the main contributions of this research are: 1) proposing an accurate RS using personality traits, demographic characteristics and time-based purchasing behavior; 2) proposing an effective and comprehensive RS for a “clothing” online store; 3) improving the RS performance by solving the cold start issue using personality traits and demographic characteristics; 4) improving the scalability issue in RS through efficient k-nearest neighbors; 5) Mitigating the sparsity issue by using personality traits and demographic characteristics and also by densifying the user-item matrix and 6) improving the RS accuracy by solving the interest drift issue through developing a time-based user-item matrix.

Collaborative filtering based recommender systems (CF–RS) are widely used to recommend products based on consumers' preference similarity. Recommendations by CF–RS merely provide suggestions as “people who bought this also bought this” while, consumers are unaware about the source of these recommendations. By amalgamating CF–RS with consumers' social network information, e-commerce sites can offer recommendation from social networks of consumers. These social network embedded systems are known as social recommender systems (SRS). The extant literature has researched on the algorithms and implementation of these systems; however, SRS have not been understood from consumers' psychological perspective. This study aims to qualitatively explore consumers' motives to accept SRS in e-commerce websites.

This qualitative study is based on in-depth interviews of frequent online shoppers. SRS are currently not very widespread in the Indian e-commerce space; hence, a vignette was shown to respondents before they responded to the questions. Inductive qualitative content analysis method was used to analyse these interviews.

Three main themes (social-gratification, self-gratification and information-gratification) emerged from the analysis. Out of these, social-gratification acts as an enabler, while self-gratification along with some elements of information-gratification act as inhibitors towards acceptance of social recommendations. Based on these gratifications, we present a conceptual model on consumer's acceptance of social recommendations.

This study is an initial attempt to qualitatively understand consumers' attitudes and acceptance of social recommendations on e-commerce websites, which in itself is a fairly new phenomenon.

Recommender systems (RS) are designed to communicate with users and drive consumers' engagement with the platform. However, little is known about the strength of this relationship and how RS can create stronger consumer engagement (CE) with the platform brand. Addressing this gap, this paper examines the role of RS in converting consumers' short-term engagement with the RS to their longer-term platform engagement.

To explore these issues, the authors review key literature in the areas of CE and RS, from which they develop a conceptual framework.

The proposed framework suggests RS design as an important precursor to consumers' RS use, which is expected to affect their platform engagement/disengagement, in turn impacting the firm's long-term outcomes. The authors also identify key managerial tactics, strategies and challenges to aid the conversion of consumers' RS to CE.

This research raises pertinent implications for research on the RS/CE interface, as synthesized in a proposed research agenda.

Based on the attained insight, authors outline implications for managing, facilitating and leveraging the proposed RS to CE conversion process. Correspondingly, authors argue that, to optimize RS effectiveness, RS designers should understand the nature of CE.

By exploring the effect of consumers' RS on their longer-term CE with the platform, the analyses offer pioneering managerial insight into RS effectiveness from a CE perspective.

Although digitalization in the workplace is burgeoning, tools are needed to facilitate personalized learning in informal learning settings. Existing knowledge recommendation techniques do not account for dynamic and task-oriented user preferences. The purpose of this paper is to propose a new design of a knowledge recommender system (RS) to fill this research gap and provide guidance for practitioners on how to enhance the effectiveness of workplace learning.

This study employs the design science research approach. A novel hybrid knowledge recommendation technique is proposed. An experiment was carried out in a case company to demonstrate the effectiveness of the proposed system design. Quantitative data were collected to investigate the influence of personalized knowledge service on users’ learning attitude.

The proposed personalized knowledge RS obtained satisfactory user feedback. The results also show that providing personalized knowledge service can positively influence users’ perceived usefulness of learning.

This research highlights the importance of providing digital support for workplace learners. The proposed new knowledge recommendation technique would be useful for practitioners and developers to harness information technology to facilitate workplace learning and effect organization learning strategies.

This study expands the scope of research on RS and workplace learning. This research also draws scholarly attention to the effective utilization of digital techniques, such as a RS, to support user decision making in the workplace.

Social network platforms are considered today as a major communication mean. Their success leads to an unprecedented growth of user-generated content; therefore, finding interesting content for a given user has become a major issue. Recommender systems allow these platforms to personalize individual experience and increase user engagement by filtering messages according to user interest and/or neighborhood. Recent research results show, however, that this content personalization might increase the echo chamber effect and create filter bubbles that restrain the diversity of opinions regarding the recommended content.

The purpose of this paper is to present a thorough study of communities on a large Twitter data set that quantifies the effect of recommender systems on users’ behavior by creating filter bubbles. The authors further propose their community-aware model (CAM) that counters the impact of different recommender systems on information consumption.

The authors propose their CAM that counters the impact of different recommender systems on information consumption. The study results show that filter bubbles effects concern up to 10% of users and the proposed model based on the similarities between communities enhance recommendations.

The authors proposed the CAM approach, which relies on similarities between communities to re-rank lists of recommendations to weaken the filter bubble effect for these users.

The advance of technology creates new possibilities for enhancing shopper experience. The purpose of this paper is to gain understanding of a recent innovation found in retail environment, a recommender system (RS). Specifically, this study investigated how the retailer’s claims of RS affect consumers’ perception of personalization, and further, trusting beliefs and intentions. Additionally, the effect of sponsored recommendation (SR) on consumers’ perceived trust was explored.

A 2 (RS claim: personalized/non-personalized)×2 (SR: present/absent)×2 (involvement: high/low) between subject factorial design was employed. An online experiment was conducted. A total of 273 response collected through Amazon MTurk were used for the analysis.

The findings showed retailer’s claims for RS were enough to increase the perception of personalization. The increased perceived personalization of the RS increased trusting beliefs and trusting intention. For SR, mixed results were found. Disclosing SR increased trusting intentions under the low-involvement condition, but the opposite effect was found under high-involvement condition.

The findings highlight the importance of retailers’ articulating what RS does. This can impact trusting beliefs and trusting intention. Additionally, the findings indicate SRs should be presented in accordance to the decision-making stage. The presence of SRs during the searching stage may positively impact consumer’s perception, but their presence during purchase stage may have a negative impact.

This study is among the first to examine the effect of different retailer’s claims on how the recommendations are generated on shopper’s perception. Also, this is one of few studies to investigate how SRs in RSs impact a shopper’s perception. This research provides insights into how an RS found in retail environment influence shopping experience.

Collaborative filtering (CF), one of the most popular recommendation techniques, is based on the principle of word-of-mouth communication between other like-minded users. The process of identifying these like-minded or similar users remains crucial for a CF framework. Conventionally, a neighbor is the one among the similar users who has rated the item under consideration. To select neighbors by the existing practices, their similarity deteriorates as many similar users might not have rated the item under consideration. This paper aims to address the drawback in the existing CF method where “not-so-similar” or “weak” neighbors are selected.

The new approach proposed here selects neighbors only on the basis of highest similarity coefficient, irrespective of rating the item under consideration. Further, to predict missing ratings by some neighbors for the item under consideration, ordinal logistic regression based on item–item similarity is used here.

Experiments using the MovieLens (ml-100) data set prove the efficacy of the proposed approach on different performance evaluation metrics such as accuracy and classification metrics. Apart from higher prediction quality, coverage values are also at par with the literature.

This new approach gets its motivation from the principle of the CF method to rely on the opinion of the closest neighbors, which seems more meaningful than trusting “not-so-similar” or “weak” neighbors. The static nature of the neighborhood addresses the scalability issue of CF. Use of ordinal logistic regression as a prediction technique addresses the statistical inappropriateness of other linear models to make predictions for ordinal scale ratings data.

Multi-criteria recommender systems (MC-RSs) allow users to express their preference in multiple aspects. Bayesian flexible mixture model (BFMM) is a model-based RS which extends FMM from single-criterion to MC. However, results of BFMM have a preference on different rating pattern problem. In single-criterion, FMM with decoupled normalization and W’s transposed function try to solve this problem. However, these techniques are applied to each criterion separately. Then, the relationship among criteria will be lost. This paper aims to solve different rating pattern problems and loss of the relationship between criteria.

The proposed method is combining between BFMM and rating conversion. First, mean and variance normalization is applied to make MC ratings of an active user and a neighbor lying on the same plane. After that, a pattern of each user is extracted using principal component analysis (PCA). Next, the pattern is used to convert neighbors’ MC ratings to the active user aspect. After that, converted MC ratings of neighbors are aggregated to be overall ratings using multiple linear regression (MLR). Finally, overall rating of the active user toward the target item is predicted using weighted average on the derived neighbors’ overall ratings where the similarity from BFMM acts as a weight.

The experimental results show that the proposed method where all criteria ratings are converted simultaneously can improve the performance of recommendation.

The proposed method predicts overall rating of the active user by converting MC ratings of each neighbor to the active user aspect at the same time, which can reduce the loss of the relationship between criteria.

Based on consideration of learner needs for expanding vocabulary and the complexity of educational content, this paper introduces a model aimed at facilitating English vocabulary learning.

By measuring a set of effective variables regarding simplicity of English sentences, a ranking algorithm is presented in the proposed model. According to this ranking, the simplest sentence in the recommender system (RS) is selected and recommended to the user. Furthermore, Pearson correlation coefficient was used for checking the degree of correlation among the respective parameters on sentence simplicity. For evaluating the efficiency of the recommended algorithm, a prototype was designed by programming using Embarcadero Delphi XE2.

The results of the study indicated that the correlation among the parameters of word frequency, sentence length and average dependency distance were 0.723, 0.683 and 0.589, respectively. The computed final score is considered to be more accurate.

The application of RS in language learning and education sheds light on the theoretical validity of system thinking by highlighting its key features: its multidisciplinary nature, complexity, dynamicity and the interdependence and relation of micro and macro levels in a system.

The proposed method has significant pedagogical implications; it can be used by second language teachers and learners for checking the degree of complexity/learnability of discourse and text.

This paper proposes an alternate model with a significantly higher speed for computing final sentence score.