Search results

With an increase in the amount of multilingual content on the World Wide Web, users are often striving to access information provided in a language of which they are non-native speakers. The purpose of this paper is to present a comprehensive study of user profile representation techniques and investigate their use in personalized cross-language information retrieval (CLIR) systems through the means of personalized query expansion.

The user profiles consist of weighted terms computed by using frequency-based methods such as tf-idf and BM25, as well as various latent semantic models trained on monolingual documents and cross-lingual comparable documents. This paper also proposes an automatic evaluation method for comparing various user profile generation techniques and query expansion methods.

Experimental results suggest that latent semantic-weighted user profile representation techniques are superior to frequency-based methods, and are particularly suitable for users with a sufficient amount of historical data. The study also confirmed that user profiles represented by latent semantic models trained on a cross-lingual level gained better performance than the models trained on a monolingual level.

Previous studies on personalized information retrieval systems have primarily investigated user profiles and personalization strategies on a monolingual level. The effect of utilizing such monolingual profiles for personalized CLIR remains unclear. The current study fills the gap by a comprehensive study of user profile representation for personalized CLIR and a novel personalized CLIR evaluation methodology to ensure repeatable and controlled experiments can be conducted.

This chapter reviews the recent developments at the intersection of personalization and AI in marketing and related fields. We provide a formal definition of personalized policy and review the methodological approaches available for personalization. We discuss scalability, generalizability, and counterfactual validity issues and briefly touch upon advanced methods for online/interactive/dynamic settings. We then summarize the three evaluation approaches for static policies – the Direct method, the Inverse Propensity Score (IPS) estimator, and the Doubly Robust (DR) method. Next, we present a summary of the evaluation approaches for special cases such as continuous actions and dynamic settings. We then summarize the findings on the returns to personalization across various domains, including content recommendation, advertising, and promotions. Next, we discuss the work on the intersection between personalization and welfare. We focus on four of these welfare notions that have been studied in the literature: (1) search costs, (2) privacy, (3) fairness, and (4) polarization. We conclude with a discussion of the remaining challenges and some directions for future research.

This paper aims to discuss and test the claim that utilization of the personalization techniques can be valuable to improve the efficiency of collaborative information retrieval (CIR) systems.

A new personalized CIR system, called PERCIRS, is presented based on the user profile similarity calculation (UPSC) formulas. To this aim, the paper proposes several UPSC formulas as well as two techniques to evaluate them. As the proposed CIR system is personalized, it could not be evaluated by Cranfield, like evaluation techniques (e.g. TREC). Hence, this paper proposes a new user‐centric mechanism, which enables PERCIRS to be evaluated. This mechanism is generic and can be used to evaluate any other personalized IR system.

The results show that among the proposed UPSC formulas in this paper, the (query‐document)‐graph based formula is the most effective. After integrating this formula into PERCIRS and comparing it with nine other IR systems, it is concluded that the results of the system are better than the other IR systems. In addition, the paper shows that the complexity of the system is less that the complexity of the other CIR systems.

This system asks the users to explicitly rank the returned documents, while explicit ranking is still not widespread enough. However it believes that the users should actively participate in the IR process in order to aptly satisfy their needs to information.

The value of this paper lies in combining collaborative and personalized IR, as well as introducing a mechanism which enables the personalized IR system to be evaluated. The proposed evaluation mechanism is very valuable for developers of personalized IR systems. The paper also introduces some significant user profile similarity calculation formulas, and two techniques to evaluate them. These formulas can also be used to find the user's community in the social networks.

This study aims to propose a consensus model that considers dynamic trust and the hesitation degree of the expert's evaluation, and the model can provide personalized adjustment advice to inconsistent experts.

The trust degree between experts will be affected by the decision-making environment or the behavior of other experts. Therefore, based on the psychological “similarity-attraction paradigm”, an adjustment method for the trust degree between experts is proposed. In addition, we proposed a method to measure the hesitation degree of the expert's evaluation under the multi-granular probabilistic linguistic environment. Based on the hesitation degree of evaluation and trust degree, a method for determining the importance degree of experts is proposed. In the feedback mechanism, we presented a personalized adjustment mechanism that can provide the personalized adjustment advice for inconsistent experts. The personalized adjustment advice is accepted readily by inconsistent experts and ensures that the collective consensus degree will increase after the adjustment.

The results show that the consensus model in this paper can solve the social network group decision-making problem, in which the trust degree among experts is dynamic changing. An illustrative example demonstrates the feasibility of the proposed model in this paper. Simulation experiments have confirmed the effectiveness of the model in promoting consensus.

The authors presented a novel dynamic trust consensus model based on the expert's hesitation degree and a personalized adjustment mechanism under the multi-granular probabilistic linguistic environment. The model can solve a variety of social network group decision-making problems.

The purpose of the paper is to conduct an exploratory study that proposes a personalized knowledge integration platform for digital libraries which can provide users with personalized information and knowledge services.

A prototype system (PIKIP_DL) is designed and developed with two types of service, i.e. personalized information/knowledge service and personalized subject category service. Evaluation of the PIKIP_DL by domain specialists and software experts is conducted. Comments are implications are addressed.

The main findings include the following: the proposed system can help suggest materials that readers are interested in for DL; the proposed system can help construct knowledge contents in a hierarchical structure; and a common recommendation concerning knowledge structure from the reviewers is that the proposed system should add a self‐organizing knowledge map function that would allow users to view knowledge subjects in a graphic manner.

The results from the evaluation of reviewers revealed that the proposed PIKIP_DL is acceptable to the integration of both personalized information service and personalized knowledge subject service. This implies that librarians and DL software agents should place emphasis on integrated service development to attract the attention of their users. Towards this goal, they could explain that personalized services (e.g. material recommendation, message recommendation, knowledge subject materials) with a mechanism of multi‐resource integration can help provide DL resources according to users' needs and wants, and in consequence to enhance DL service efficacy.

The research describes the importance of information/knowledge integration with respect to its support on the learning and study methods of users, and has developed a personalized knowledge integration platform as a mechanism that provides a personalized information service and a personalized knowledge subject category service. By employing Apriori algorithm and association rules as the data mining mechanism, personalized information recommendations are derived from circulation data, and a knowledge subject category is integrated from online sharing knowledge by participants.

Purpose — To develop methodologies to evaluate search engines according to an individual's preference in an easy and reliable manner, and to formulate user-oriented metrics to compare freshness and duplication in search results.

Design/methodology/approach — A personalised evaluation model for comparing search engines is designed as a hierarchy of weighted parameters. These commonly found search engine features and performance measures are given quantitative and qualitative ratings by an individual user. Furthermore, three performance measurement metrics are formulated and presented as histograms for visual inspection. A methodology is introduced to quantitatively compare and recognise the different histogram patterns within the context of search engine performance.

Findings — Precision and recall are the fundamental measures used in many search engine evaluations due to their simplicity, fairness and reliability. Most recent evaluation models are user oriented and focus on relevance issues. Identifiable statistical patterns are found in performance measures of search engines.

Research limitations/implications — The specific parameters used in the evaluation model could be further refined. A larger scale user study would confirm the validity and usefulness of the model. The three performance measures presented give a reasonably informative overview of the characteristics of a search engine. However, additional performance parameters and their resulting statistical patterns would make the methodology more valuable to the users.

Practical implications — The easy-to-use personalised search engine evaluation model can be tailored to an individual's preference and needs simply by changing the weights and modifying the features considered. A user is able to get an idea of the characteristics of a search engine quickly using the quantitative measure of histogram patterns that represent the search performance metrics introduced.

Originality/value — The presented work is considered original as one of the first search engine evaluation models that can be personalised. This enables a Web searcher to choose an appropriate search engine for his/her needs and hence finding the right information in the shortest time with the least effort.

This paper aims to investigate the role of five highly relevant advertiser- (i.e. personalization and ad placement) and consumer-controlled (i.e. privacy concerns, perceived relevance and Facebook motives) factors in the evaluation and perceived outcomes of personalized Facebook advertising as well as how these factors interrelate.

Twenty-eight semi-structured interviews, in which elicitation techniques were used, were carried out among 25- to 55-year-old Facebook users.

The findings point to a complex tradeoff between the risks and benefits of personalized Facebook advertising, in which perceived relevance and Facebook use motives play a vital role.

This study focused on the general Facebook advertising experience, yet the elicitation techniques were applied only on the desktop website. Future research should look further into mobile advertising formats.

Personalization and retargeting algorithms could be improved and ads should be designed with the customers’ interests in mind to improve their effectiveness and reduce privacy concerns.

Social media advertising innovates at a high pace. Yet, the literature shows an urgent need for research into which ad formats and characteristics appeal to users and why (or why not). Qualitative studies into the determinants of advertising outcomes are scarce but highly needed because they can uncover complex interactions between factors and thus provide a deeper understanding.

The purpose of this paper is to improve the customer satisfaction by offering online personalized recommendation system.

By employing an innovative associative classification method, this paper is able to predict a customer’s pleasure during the online while-recommending process. Consumers can make an active decision to recommended products. Based on customer’s characteristics, a product will be recommended to the potential buyer if the model predicts that he/she will click to view the product. That is, he/she is satisfied with the recommended product. Finally, the feasibility of the proposed recommendation system is validated through a Taobao shop.

The results of the experimental study clearly show that the online personalized recommendation system maximizes the customer’s satisfaction during the online while-recommending process based on an innovative associative classification method on the basis of consumer initiative decision.

Conventionally, customers are considered as passive recipients of the recommendation system. However, customers are tired of the recommendation system, and they can do nothing sometimes. This paper designs a new recommendation system on the basis of consumer initiative decision. The proposed recommendation system maximizes the customer’s satisfaction during the online while-recommending process.

The purpose of this co-produced research project was to conduct interviews with people working in, volunteering with and accessing Canadian recovery colleges (RCs) to explore their perspectives on what an evaluation strategy for RCs could look like.

This study used a participatory action research approach and involved semistructured interviews with 29 people involved with RCs across Canada.

In this paper, the authors share insights from participants about the purposes of RC evaluation; key elements of evaluation; and the most applicable and effective approaches to evaluation. Participants indicated that RC evaluations should use a personalized, humanistic and accessible approach. The findings suggest that evaluations can serve multiple purposes and have the potential to support both organizational and personal-recovery goals if they are developed with meaningful input from people who access and work in RCs.

The findings can be used to guide evaluations in which aspects that are most important to those involved in RCs could inform choices, decisions, priorities, developments and adaptations in RC evaluation processes and, ultimately, in programming.

A recent scoping review revealed that although coproduction is a central feature of the RC model, coproduction principles are rarely acknowledged in descriptions of how RC evaluation strategies are developed. Exploring coproduction processes in all aspects of the RC model, including evaluation, can further the mission of RCs, which is to create spaces where people can come together and engage in mutual capacity-building and collaboration.