Search results

1 – 10 of over 20000
To view the access options for this content please click here
Article
Publication date: 2 February 2010

Daniela Godoy, Silvia Schiaffino and Analía Amandi

Recommender agents are used to make recommendations of interesting items in a wide variety of application domains, such as web page recommendation, music, e‐commerce…

Abstract

Purpose

Recommender agents are used to make recommendations of interesting items in a wide variety of application domains, such as web page recommendation, music, e‐commerce, movie recommendation, tourism, restaurant recommendation, among others. Despite the various and different domains in which recommender agents are used and the variety of approaches they use to represent user interests and make recommendations, there is some functionality that is common to all of them, such as user model management and recommendation of interesting items. This paper aims at generalizing these common behaviors into a framework that enables developers to reuse recommender agents' main characteristics in their own developments.

Design/methodology/approach

This work presents a framework for recommendation that provides the control structures, the data structures and a set of algorithms and metrics for different recommendation methods. The proposed framework acts as the base design for recommender agents or applications that want to add the already modeled and implemented capabilities to their own functionality. In contrast with other proposals, this framework is designed to enable the integration of diverse user models, such as demographic, content‐based and item‐based. In addition to the different implementations provided for these components, new algorithms and user model representations can be easily added to the proposed approach. Thus, personal agents originally designed to assist a single user can reuse the behavior implemented in the framework to expand their recommendation strategies.

Findings

The paper describes three different recommender agents built by materializing the proposed framework: a movie recommender agent, a tourism recommender agent, and a web page recommender agent. Each agent uses a different recommendation approach. PersonalSearcher, an agent originally designed to suggest interesting web pages to a user, was extended to collaboratively assist a group of users using content‐based algorithms. MovieRecommender recommends interesting movies using an item‐based approach and Traveller suggests holiday packages using demographic user models. Findings encountered during the development of these agents and their empirical evaluation are described here.

Originality/value

The advantages of the proposed framework are twofold. On the one hand, the functionality provided by the framework enables the development of recommender agents without the need for implementing its whole set of capabilities from scratch. The main processes and data structures of recommender agents are already implemented. On the other hand, already existing agents can be enhanced by incorporating the functionality provided by the recommendation framework in order to act collaboratively.

Details

Internet Research, vol. 20 no. 1
Type: Research Article
ISSN: 1066-2243

Keywords

To view the access options for this content please click here
Article
Publication date: 15 June 2012

Andrea Barraza‐Urbina and Angela Carrillo Ramos

The purpose of this paper is to describe UWIRS (Ubiquitous Web Information Retrieval Solution), an agent‐based Web Information Retrieval (WIR) solution designed taking…

Abstract

Purpose

The purpose of this paper is to describe UWIRS (Ubiquitous Web Information Retrieval Solution), an agent‐based Web Information Retrieval (WIR) solution designed taking into account the unique features of the World Wide Web (WWW) and the limitations of existing WIR solutions for ubiquitous environments.

Design/methodology/approach

UWIRS can offer recommendation services by using the Multi‐Agent Vizier Recommendation Framework (Vizier). Vizier was designed under a generic approach and therefore can provide services to information retrieval applications so these may offer product recommendations that consider several adaptation/personalization dimensions (e.g. user dimension, context, among others).

Findings

Overall, the main challenge resides on: location, retrieval, integration and presentation of information from the WWW, quickly and accurately, to satisfy a user's singular information needs.

Originality/value

In UWIRS, agents cooperate in order to retrieve personalized information, considering user needs, goals, preferences and contextual features. UWIRS's agents are responsible for: interpreting user input and adding adaptation information by means of a query enrichment process; identifying and selecting the appropriate data sources taking into consideration the Profile Set (composed of User, Device and Information‐Provider Profiles); executing query routing and the information retrieval process; integrating and filtering the retrieved results; and lastly, coherent presentation of quality and relevant ubiquitous information (anytime, anywhere and anyhow) that satisfies the user's particular information needs and constraints associated to his/her access device.

Details

International Journal of Web Information Systems, vol. 8 no. 2
Type: Research Article
ISSN: 1744-0084

Keywords

To view the access options for this content please click here
Article
Publication date: 1 November 2002

Timothy K. Shih, Chuan‐Feng Chiu, Hui‐huang Hsu and Fuhua Lin

The Internet has become a popular medium for information exchange and knowledge delivery. Several traditional social activities have moved to the Internet, such as…

Downloads
2099

Abstract

The Internet has become a popular medium for information exchange and knowledge delivery. Several traditional social activities have moved to the Internet, such as distance learning, tele‐medical system and. traditional buying and selling activities. Online merchants must know what users want, so providing recommendation services is an important strategy. Analyzes users’ on‐line behavior and interests, and recommends to them new or potential products. The analysis mechanism is based on the correlation among customers, product items, and product features. An algorithm is developed to classify users into groups and the recommendation is based on the classification. The system can help merchants to make suitable business decisions and provide personalized information to the customers. A generic mobile agent framework for e‐commerce applications is proposed. The aforementioned collaborative computing architecture for the recommendation system is based on the framework.

Details

Industrial Management & Data Systems, vol. 102 no. 8
Type: Research Article
ISSN: 0263-5577

Keywords

To view the access options for this content please click here
Article
Publication date: 5 August 2014

Anyuan Shen

The purpose of this paper is an exploratory study of customers’ “lived” experiences of commercial recommendation services to better understand customer expectations for…

Downloads
4638

Abstract

Purpose

The purpose of this paper is an exploratory study of customers’ “lived” experiences of commercial recommendation services to better understand customer expectations for personalization with recommendation agents. Recommendation agents programmed to “learn” customer preferences and make personalized recommendations of products and services are considered a useful tool for targeting customers individually. Some leading service firms have developed proprietary recommender systems in the hope that personalized recommendations could engage customers, increase satisfaction and sharpen their competitive edge. However, personalized recommendations do not always deliver customer satisfaction. More often, they lead to dissatisfaction, annoyance or irritation.

Design/methodology/approach

The critical incident technique is used to analyze customer satisfactory or dissatisfactory incidents collected from online group discussion participants and bloggers to develop a classification scheme.

Findings

A classification scheme with 15 categories is developed, each illustrated with satisfactory incidents and dissatisfactory incidents, defined in terms of an underlying customer expectation, typical instances of satisfaction and dissatisfaction and, when possible, conditions under which customers are likely to have such an expectation. Three pairs of themes emerged from the classification scheme. Six tentative research propositions were introduced.

Research limitations/implications

Findings from this exploratory research should be regarded as preliminary. Besides, content validity of the categories and generalizability of the findings should be subject to future research.

Practical implications

Research findings have implications for identifying priorities in developing algorithms and for managing personalization more strategically.

Originality/value

This research explores response to personalization from a customer’s perspective.

Details

Journal of Services Marketing, vol. 28 no. 5
Type: Research Article
ISSN: 0887-6045

Keywords

To view the access options for this content please click here
Article
Publication date: 4 October 2017

Giuseppe Pedeliento, Daniela Andreini, Mara Bergamaschi and Jane Elizabeth Klobas

The purpose of this paper is to evaluate how the intermediation of an online agent in the relationship between prospective clients and professional service providers…

Abstract

Purpose

The purpose of this paper is to evaluate how the intermediation of an online agent in the relationship between prospective clients and professional service providers affects individual purchasing processes and decisions, and satisfaction with the professional service provider once the commercial transaction is concluded.

Design/methodology/approach

Drawing on the integrated trust-technology acceptance model, modified to include two additional variables to take into account of the specificities of the context investigated – users’ perceived reduction of information asymmetry and satisfaction with the professional service provider – a research framework is developed and tested with a research design combining a decision tree procedure with structural equation modelling and multi-group analysis. Participants are 188 users of an Italian website which incorporates an online agent that refers notaries to prospective clients.

Findings

Decisions to purchase professional services brokered by online agents depend upon trust in the agent, and users’ perceptions of the agent’s ability to reduce information asymmetry, as well as its perceived usefulness. Online agents for professional services can be effective as well as efficient: users who bought the service from an agent-referred notary had higher levels of satisfaction with their professional service provider than users who purchased the service from a different notary.

Originality/value

This is the first empirical effort to investigate the effects of online agents in the specific context of professional service purchasing. The uniqueness of the research context permitted identification of a new type of online agent, the “double-sided online referral agent”.

Details

Journal of Service Theory and Practice, vol. 27 no. 6
Type: Research Article
ISSN: 2055-6225

Keywords

To view the access options for this content please click here
Article
Publication date: 8 June 2010

Kyle B. Murray, Jianping Liang and Gerald Häubl

This paper seeks to review current research on assistive consumer technologies (ACT 1.0) and to discuss a series of research challenges that need to be addressed before…

Downloads
1462

Abstract

Purpose

This paper seeks to review current research on assistive consumer technologies (ACT 1.0) and to discuss a series of research challenges that need to be addressed before the field can move towards tools that are more effective and more readily adopted by consumers (ACT 2.0).

Design/methodology/approach

This is a conceptual paper. The perspective, commensurate with the current research and areas of expertise, is that of consumer researchers.

Findings

The paper argues that, while substantial advances have been made in the technical design of ACTs – and the algorithms that power recommendation systems, there are substantial barriers to wide‐scale consumer adoption of such tools that need to be addressed. In particular, future ACT designs will need to better integrate current research in human judgment and decision making to improve the ease with which such tools can be used.

Originality/value

From the perspective of consumer researchers, the paper highlights a set of key areas of enquiry that have the potential to substantially advance assistive consumer technology research.

Details

Internet Research, vol. 20 no. 3
Type: Research Article
ISSN: 1066-2243

Keywords

To view the access options for this content please click here
Article
Publication date: 7 November 2016

Congying Guan, Shengfeng Qin, Wessie Ling and Guofu Ding

With the developments of e-commerce markets, novel recommendation technologies are becoming an essential part of many online retailers’ economic models to help drive…

Downloads
1554

Abstract

Purpose

With the developments of e-commerce markets, novel recommendation technologies are becoming an essential part of many online retailers’ economic models to help drive online sales. Initially, the purpose of this paper is to undertake an investigation of apparel recommendations in the commercial market in order to verify the research value and significance. Then, this paper reviews apparel recommendation techniques and systems through academic research, aiming to acquaint apparel recommendation context, summarize the pros and cons of various research methods, identify research gaps and eventually propose new research solutions to benefit apparel retailing market.

Design/methodology/approach

This study utilizes empirical research drawing on 130 academic publications indexed from online databases. The authors introduce a three-layer descriptor for searching articles, and analyse retrieval results via distribution graphics of years, publications and keywords.

Findings

This study classified high-tech integrated apparel systems into 3D CAD systems, personalised design systems and recommendation systems. The authors’ research interest is focussed on recommendation system. Four types of models were found, namely clothes searching/retrieval, wardrobe recommendation, fashion coordination and intelligent recommendation systems. The forth type, smart systems, has raised more awareness in apparel research as it is equipped with advanced functions and application scenarios to satisfy customers. Despite various computational algorithms tested in system modelling, existing research is lacking in terms of apparel and users profiles research. Thus, from the review, the authors have identified and proposed a more complete set of key features for describing both apparel and users profiles in a recommendation system.

Originality/value

Based on previous studies, this is the first review paper on this topic in this subject field. The summarised work and the proposed new research will inspire future researchers with various knowledge backgrounds, especially, from a design perspective.

Details

International Journal of Clothing Science and Technology, vol. 28 no. 6
Type: Research Article
ISSN: 0955-6222

Keywords

To view the access options for this content please click here
Article
Publication date: 8 June 2010

Nayat Sanchez‐Pi and Jose Manuel Molina

Taking into account the importance of e‐commerce and the current applications of AI techniques in this area, this research aims to adequate the design of a multi‐agent

Abstract

Purpose

Taking into account the importance of e‐commerce and the current applications of AI techniques in this area, this research aims to adequate the design of a multi‐agent system for the provisioning of e‐services in u‐commerce environments. This proposal is centred on the methods of evaluation in a u‐e‐commerce environment.

Design/methodology/approach

The multi‐agent systems (MAS) approach is based on an MAS model developed for AmI that has been redesigned to support u‐commerce. The use of a recommendation system, previously developed by the research group, is suggested for this MAS. The methodological proposal centres on the evaluation of this type of system.

Findings

The evaluation of this type of system is the principal problem of current research. Therefore, this is the main contribution of the paper.

Research limitations/implications

The different evaluation methods that are proposed, whether qualitative or quantitative, offer the possibility of measuring the added value that the context can give to the use of e‐services in different domains of application. Qualitative evaluation should consider the customer as a central piece in the system. In addition, quantitative methods should objectively evaluate the contribution of context to the application.

Practical implications

At present, there is no single method for evaluating the benefits of different u‐commerce systems, so a new method needs to be found based on these techniques.

Originality/value

The research proposes an MAS designed for u‐commerce domains, analyzes the capacity of trust management techniques in this environment, and proposes several evaluation methods to show the benefits of context information in the use of e‐services. Several real developments are described to show the different applications of MAS in u‐commerce and how evaluation is carried out.

Details

Internet Research, vol. 20 no. 3
Type: Research Article
ISSN: 1066-2243

Keywords

To view the access options for this content please click here
Article
Publication date: 16 April 2020

Qiaoling Zhou

English original movies played an important role in English learning and communication. In order to find the required movies for us from a large number of English original…

Abstract

Purpose

English original movies played an important role in English learning and communication. In order to find the required movies for us from a large number of English original movies and reviews, this paper proposed an improved deep reinforcement learning algorithm for the recommendation of movies. In fact, although the conventional movies recommendation algorithms have solved the problem of information overload, they still have their limitations in the case of cold start-up and sparse data.

Design/methodology/approach

To solve the aforementioned problems of conventional movies recommendation algorithms, this paper proposed a recommendation algorithm based on the theory of deep reinforcement learning, which uses the deep deterministic policy gradient (DDPG) algorithm to solve the cold starting and sparse data problems and uses Item2vec to transform discrete action space into a continuous one. Meanwhile, a reward function combining with cosine distance and Euclidean distance is proposed to ensure that the neural network does not converge to local optimum prematurely.

Findings

In order to verify the feasibility and validity of the proposed algorithm, the state of the art and the proposed algorithm are compared in indexes of RMSE, recall rate and accuracy based on the MovieLens English original movie data set for the experiments. Experimental results have shown that the proposed algorithm is superior to the conventional algorithm in various indicators.

Originality/value

Applying the proposed algorithm to recommend English original movies, DDPG policy produces better recommendation results and alleviates the impact of cold start and sparse data.

Details

International Journal of Intelligent Computing and Cybernetics, vol. 13 no. 1
Type: Research Article
ISSN: 1756-378X

Keywords

To view the access options for this content please click here
Article
Publication date: 24 May 2021

Tao Liu, Weiquan Wang, Jingjun (David) Xu, Donghong Ding and Honglin Deng

This paper investigates the effects of advising strength of a recommendation agent on users' trust and distrust beliefs and how the effects are moderated by perceived…

Abstract

Purpose

This paper investigates the effects of advising strength of a recommendation agent on users' trust and distrust beliefs and how the effects are moderated by perceived brand familiarity.

Design/methodology/approach

A research model is evaluated using a laboratory experiment with 149 participants.

Findings

Results reveal that a strong advising tone leads to higher trust in terms of users' credibility and benevolence beliefs and lower distrust in terms of their discredibility beliefs (the trustor's concerns regarding the trustee's dishonesty and competence in engaging in harmful behavior) when perceived brand familiarity is high. By contrast, when brand familiarity is low, strong advising tone results in low trust in terms of users' credibility belief and high distrust in terms of their beliefs in discredibility and malevolence (concerns regarding the trustee's conduct in terms of a malicious intention that can hurt the trustor's welfare).

Originality/value

This paper contributes to the trust and distrust literature by studying how each of the dimensions of trust and distrust can be affected by an RA's design feature. It extends the attribution theory to the RA context by studying the moderating role of brand familiarity in determining the effects of the advising strength of an RA. It provides actionable guidelines for practitioners regarding the adoption of an RA's appropriate advising strength to promote different types of products.

Details

Information Technology & People, vol. 34 no. 7
Type: Research Article
ISSN: 0959-3845

Keywords

1 – 10 of over 20000