Extending web-based educational systems with personalised support through User Centred Designed recommendations along the e-learning life cycle

In this paper we address an open key issue during the development of web-based educational systems. In particular, we provide an educational-oriented approach for building personalised e-learning environments that focuses on putting the learners' needs in the centre of the development process. Our approach proposes user centred design methodologies involving interdisciplinary teams of software developers and domain experts. It is illustrated in an adaptive e-learning system, where a MOOC (Massive Open Online Course) was taken by nearly 400 learners. In particular, we report where user centred design methods can be applied along the e-learning life cycle to designing and evaluating personalisation support through recommendations in learning management systems.     

Hybrid recommendations for mobile commerce based on mobile phone features

Mobile data communications have evolved as the number of third generation (3G) subscribers has increased. The evolution has triggered an increase in the use of mobile devices, such as mobile phones, to conduct mobile commerce and mobile shopping on the mobile web. There are fewer products to browse on the mobile web; hence, one‐to‐one marketing with product recommendations is important. Typical collaborative filtering (CF) recommendation systems make recommendations to potential customers based on the purchase behaviour of customers with similar preferences. However, this method may suffer from the so‐called sparsity problem, which means there may not be sufficient similar users because the user‐item rating matrix is sparse. In mobile shopping environments, the features of users' mobile phones provide different functionalities for using mobile services; thus, the features may be used to identify users with similar purchase behaviour. In this paper, we propose a mobile phone feature (MPF)‐based hybrid method to resolve the sparsity issue of the typical CF method in mobile environments. We use the features of mobile phones to identify users' characteristics and then cluster users into groups with similar interests. The hybrid method combines the MPF‐based method and a preference‐based method that uses association rule mining to extract recommendation rules from user groups and make recommendations. Our experiment results show that the proposed hybrid method performs better than other recommendation methods.     

Practical guidelines for designing and evaluating educationally oriented recommendations

There is a need for designing educationally oriented recommendations that deal with educational goals as well as learners' preferences and context in a personalised way. They have to be both based on educators' experience and perceived as adequate by learners. This paper compiles practical guidelines to produce personalised recommendations that are meant to foster active learning in online courses. These guidelines integrate three different methodologies: i) user centred design as defined by ISO 9241-210, ii) the e-learning life cycle of personalised educational systems, and iii) the layered evaluation of adaptation features. To illustrate guidelines actual utility, generality and flexibility, the paper describes their applicability to design educational recommendations in two different contexts, which in total involved 125 educators and 595 learners. These applications show benefits for learners and educators. Following this approach, we are targeting to cope with one of the main challenges in current massive open online courses, which are expected to provide personalised education to an increasing number of students without the continuous involvement of educators in supporting learners during their course interactions.     

Intelligent e‐government services with personalized recommendation techniques

Information overload is becoming one of the problems that hinder the effectiveness of e‐government services. Intelligent e‐government services with personalized recommendation techniques can provide a solution for this problem. Existing recommendation approaches have not entirely considered the influences of attributes of various online services and may result in no guarantee of recommendation accuracy. This study proposes a new approach to handle recommendation issues of one‐and‐only items in e‐government services. The proposed approach integrates the techniques of semantic similarity and the traditional item‐based collaborative filtering. A recommender system named Smart Trade Exhibition Finder has been developed to implement the proposed recommendation approach. The recommender system can be applied in e‐government services to improve the quality of government‐to‐business online services. © 2007 Wiley Periodicals, Inc. Int J Int Syst 22: 401–417, 2007.     

From Mobile Phone Sensing to Human Geo‐Social Behavior Understanding

The study of geo‐social behaviors has long been a scientific problem. In contrast to traditional social science, which suffers from the problems such as high data collection cost and imported user subjectivity, a new approach is presented to study social behaviors based on mobile phone sensing data. Different from other similar studies on mobile social sensing, three different types of geo‐social behaviors, including online interaction, offline interaction, and mobility patterns, are characterized based on a newly released Nokia mobile phone data set. We further discuss the impact factors to these behaviors as well as the correlation among them. The findings in this article are crucial for many different fields, ranging from urban planning, location‐based services, to social recommendation.     

User‐oriented quality for OER: understanding teachers' views on re‐use,quality, and trust

We analysed how teachers as users of open educational resources (OER) repositories act in the re‐use process and how they perceive quality. Based on a quantitative empirical study, we also surveyed which quality requirements users have and how they would contribute to the quality process. Trust in resources, organizations, and technologies seem to be of particular importance when looking at quality. In our findings, we derive recommendations for learning object repositories and OER user‐oriented quality assurance.     

A WEB‐BASED PERSONALIZED BUSINESS PARTNER RECOMMENDATION SYSTEM USING FUZZY SEMANTIC TECHNIQUES

The web provides excellent opportunities to businesses in various aspects of development such as finding a business partner online. However, with the rapid growth of web information, business users struggle with information overload and increasingly find it difficult to locate the right information at the right time. Meanwhile, small and medium businesses (SMBs), in particular, are seeking “one‐to‐one” e‐services from government in current highly competitive markets. How can business users be provided with information and services specific to their needs, rather than an undifferentiated mass of information? An effective solution proposed in this study is the development of personalized e‐services. Recommender systems is an effective approach for the implementation of Personalized E‐Service which has gained wide exposure in e‐commerce in recent years. Accordingly, this paper first presents a hybrid fuzzy semantic recommendation (HFSR) approach which combines item‐based fuzzy semantic similarity and item‐based fuzzy collaborative filtering (CF) similarity techniques. This paper then presents the implementation of the proposed approach into an intelligent recommendation system prototype called Smart BizSeeker, which can recommend relevant business partners to individual business users, particularly for SMBs. Experimental results show that the HFSR approach can help overcome the semantic limitations of classical CF‐based recommendation approaches, namely sparsity and new “cold start” item problems.     

Personalised online sales using web usage data mining

Practically every major company with a retail operation has its own web site and online sales facilities. This paper describes a toolset that exploits web usage data mining techniques to identify customer Internet browsing patterns. These patterns are then used to underpin a personalised product recommendation system for online sales. Within the architecture, a Kohonen neural network or self-organizing map (SOM) has been trained for use both offline, to discover user group profiles, and in real-time to examine active user click stream data, make a match to a specific user group, and recommend a unique set of product browsing options appropriate to an individual user. Our work demonstrates that this approach can overcome the scalability problem that is common among these types of system. Our results also show that a personalised recommender system powered by the SOM predictive model is able to produce consistent recommendations.     

一种基于用户播放行为序列的个性化视频推荐策略

本文针对在线视频服务网站的个性化推荐问题,提出了一种基于用户播放行为序列的个性化推荐策略.该策略通过深度神经网络词向量模型分析用户播放视频行为数据,将视频映射成等维度的特征向量,提取视频的语义特征.聚类用户播放历史视频的特征向量,建模用户兴趣分布矩阵.结合用户兴趣偏好和用户观看历史序列生成推荐列表.在大规模的视频服务系统中进行了离线实验,相比随机算法、基于物品的协同过滤和基于用户的协同过滤传统推荐策略,本方法在用户观看视频的Top-N推荐精确率方面平均分别获得22.3%、30.7%和934%的相对提升,在召回率指标上分别获得52.8%、41%和1065%的相对提升.进一步地与矩阵分解算法SVD++、基于双向LSTM模型和注意力机制的Bi-LSTM+Attention算法和基于用户行为序列的深度兴趣网络DIN比较,Top-N推荐精确率和召回率也得到了明显提升.该推荐策略不仅获得了较高的精确率和召回率,还尝试解决传统推荐面临大规模工业数据集时的数据要求严苛、数据稀疏和数据噪声等问题.     

Discovering internal social relationship for influence-aware service recommendation

Existing approaches, such as semantic content-based or Collaborative Filtering-based recommendations, fail to exploit social aspects of services because services lack social relationships and do not consider social influence. In this paper, we propose a methodology for connecting distributed services in a global social service network (GSSN) to facilitate discovering internal social relationship for social influence-aware service recommendation. First, we propose a novel platform for constructing a GSSN by linking distributed services with social links based on quality of social link. We then propose a flexible model of the effective awareness of social influence, which provides a quantitative measure of the strength of influence between services. Next, a novel social influence-aware service recommendation approach is proposed based on GSSN using internal social relationship among services. The experimental results demonstrated that our new approach can solve the service recommendation problem with a low usage threshold and high accuracy, where the user preferences are exploited by a recommend-as-you-go method.     

Data mining: an overview from a database perspective

Mining information and knowledge from large databases has been recognized by many researchers as a key research topic in database systems and machine learning, and by many industrial companies as an important area with an opportunity of major revenues. Researchers in many different fields have shown great interest in data mining. Several emerging applications in information-providing services, such as data warehousing and online services over the Internet, also call for various data mining techniques to better understand user behavior, to improve the service provided and to increase business opportunities. In response to such a demand, this article provides a survey, from a database researcher's point of view, on the data mining techniques developed recently. A classification of the available data mining techniques is provided and a comparative study of such techniques is presented     

A hybrid trust‐enhanced collaborative filtering recommendation approach for personalized government‐to‐business e‐services

The information overload on the World Wide Web results in the underuse of some existing e‐government services within the business domain. Small‐to‐medium businesses (SMBs), in particular, are seeking “one‐to‐one'' e‐services from government in current highly competitive markets, and there is an imperative need to develop Web personalization techniques to provide business users with information and services specific to their needs, rather than an undifferentiated mass of information. This paper focuses on how e‐governments can support businesses on the problem of selecting a trustworthy business partner to perform reliable business transactions. In the business partner selection process, trust or reputation information is crucial and has significant influence on a business user's decision regarding whether or not to do business with other business entities. For this purpose, an intelligent trust‐enhanced recommendation approach to provide personalized government‐to‐business (G2B) e‐services, and in particular, business partner recommendation e‐services for SMBs is proposed. Accordingly, in this paper, we develop (1) an implicit trust filtering recommendation approach and (2) an enhanced user‐based collaborative filtering (CF) recommendation approach. To further exploit the advantages of the two proposed approaches, we develop (3) a hybrid trust‐enhanced CF recommendation approach (TeCF) that integrates both the proposed implicit trust filtering and the enhanced user‐based CF recommendation approaches. Empirical results demonstrate the effectiveness of the proposed approaches, especially the hybrid TeCF recommendation approach in terms of improving accuracy, as well as in dealing with very sparse data sets and cold‐start users. © 2011 Wiley Periodicals, Inc.     

TWILITE: A recommendation system for Twitter using a probabilistic model based on latent Dirichlet allocation

Twitter provides search services to help people find users to follow by recommending popular users or the friends of their friends. However, these services neither offer the most relevant users to follow nor provide a way to find the most interesting tweet messages for each user. Recently, collaborative filtering techniques for recommendations based on friend relationships in social networks have been widely investigated. However, since such techniques do not work well when friend relationships are not sufficient, we need to take advantage of as much other information as possible to improve the performance of recommendations.In this paper, we propose TWILITE, a recommendation system for Twitter using probabilistic modeling based on latent Dirichlet allocation which recommends top-K users to follow and top-K tweets to read for a user. Our model can capture the realistic process of posting tweet messages by generalizing an LDA model as well as the process of connecting to friends by utilizing matrix factorization. We next develop an inference algorithm based on the variational EM algorithm for learning model parameters. Based on the estimated model parameters, we also present effective personalized recommendation algorithms to find the users to follow as well as the interesting tweet messages to read. The performance study with real-life data sets confirms the effectiveness of the proposed model and the accuracy of our personalized recommendations.     

e‐Learning recommender system for a group of learners based on the unified learner profile approach

In the age of information explosion, e‐learning recommender systems (eL_RSs) have emerged as effective information filtering techniques that attempt to provide the most appropriate learning resources for learners while using e‐learning systems. These learners are differentiated on the basis of their learning styles, goals, knowledge levels and others. Several attempts have been made in the past to design eL_RSs to recommend resources to individuals; however, an investigation of recommendations to a group of learners in e‐learning is still in its infancy. In this paper, we focus on the problem of recommending resources to a group of learners rather than to an individual. The major challenge in group recommendation is how to merge the individual preferences of different learners that form a group and extract a pseudo unified learner profile (ULP) that closely reflects the preferences of all learners. Firstly, we propose a profile merging scheme for the ULP by utilizing learning styles, knowledge levels and ratings of learners in a group. Thereafter, a collaborative approach is proposed based on the ULP for effective group recommendations. Experimental results are presented to demonstrate the effectiveness of the proposed group recommendation strategy for e‐learning.     

Collaborative filtering and deep learning based recommendation system for cold start items

Recommender system is a specific type of intelligent systems, which exploits historical user ratings on items and/or auxiliary information to make recommendations on items to the users. It plays a critical role in a wide range of online shopping, e-commercial services and social networking applications. Collaborative filtering (CF) is the most popular approaches used for recommender systems, but it suffers from complete cold start (CCS) problem where no rating record are available and incomplete cold start (ICS) problem where only a small number of rating records are available for some new items or users in the system. In this paper, we propose two recommendation models to solve the CCS and ICS problems for new items, which are based on a framework of tightly coupled CF approach and deep learning neural network. A specific deep neural network SADE is used to extract the content features of the items. The state of the art CF model, timeSVD++, which models and utilizes temporal dynamics of user preferences and item features, is modified to take the content features into prediction of ratings for cold start items. Extensive experiments on a large Netflix rating dataset of movies are performed, which show that our proposed recommendation models largely outperform the baseline models for rating prediction of cold start items. The two proposed recommendation models are also evaluated and compared on ICS items, and a flexible scheme of model retraining and switching is proposed to deal with the transition of items from cold start to non-cold start status. The experiment results on Netflix movie recommendation show the tight coupling of CF approach and deep learning neural network is feasible and very effective for cold start item recommendation. The design is general and can be applied to many other recommender systems for online shopping and social networking applications. The solution of cold start item problem can largely improve user experience and trust of recommender systems, and effectively promote cold start items.     

An AI-based open recommender system for personalized labor market driven education

Attaining those skills that match labor market demand is getting increasingly complicated, not in the last place in engineering education, as prerequisite knowledge, skills, and abilities are evolving dynamically through an uncontrollable and seemingly unpredictable process. Anticipating and addressing such dynamism is a fundamental challenge to twenty-first century education. The burgeoning availability of data, not only on the demand side but also on the supply side (in the form of open educational resources) coupled with smart technologies, may provide a fertile ground for addressing this challenge. In this paper, we propose a novel, Artificial Intelligence (AI) driven approach to the development of an open, personalized, and labor market oriented learning recommender system, called eDoer. We discuss the complete system development cycle starting with a systematic user requirements gathering, and followed by system design, implementation, and validation. Our recommender prototype (1) derives the skill requirements for particular occupations through an analysis of online job vacancy announcements; (2) decomposes skills into learning topics; (3) collects a variety of open online educational resources that address those topics; (4) checks the quality of those resources and topic relevance with three intelligent prediction models; (5) helps learners to set their learning goals towards their desired job-related skills; (6) recommends personalized learning pathways and learning content based on individual learning goals; and (7) provides assessment services for learners to monitor their progress towards their desired learning objectives. Accordingly, we created a learning dashboard focusing on three Data Science related jobs and conducted an initial validation of eDoer through a randomized experiment. Controlling for the effects of prior knowledge as assessed by means of a pretest, the randomized experiment provided tentative support for the hypothesis that learners who engaged with personal recommendations provided by eDoer to acquire knowledge of basic statistics, attained higher scores on the posttest than those who did not. The hypothesis that learners who received personalized content in terms of format, length, level of detail, and content type, would achieve higher scores than those receiving non-personalized content was not supported.     

User‐Centric Service Map for Identifying New Service Opportunities from Potential Needs: A Case of App Store Applications

Today, service innovation is just as important as product innovation. The ideation of service innovation, vis‐à‐vis product innovation, is user‐oriented, rather than maker‐oriented. Thus, capturing and understanding user context is key to being able to offer personalized and relevant services, and further identify new service opportunities. Therefore, a user‐centric approach is needed in new service development, especially in the era of ubiquitous service. There exists a rich literature on how to incorporate customers into new service development, but most has focused only on their expressed needs, and failed to identify potential needs. In response, this paper proposes a ‘user‐centric service map’, which first visualizes the portfolio of existing services based on the dictionary of potential needs and then helps to investigate vacuums that can provide a concrete shape for new service opportunities. The suggested approach is composed of three parts: first, constructing a potential needs dictionary, second, developing a service map, and finally, identifying new service opportunities. A case study of Apple's App Store services is conducted to verify the feasibility and utility of the proposed approach and offer strategic implications.     

A software architecture for virtualized educational multimedia games in IPTV environments

T‐Learning makes it possible to deliver educational content to home TVs. TV operators, which manage huge populations of devices such as set‐top‐boxes (STBs) in user homes, are considering t‐Learning as an interesting option for expanding the service they offer. However, typical STB hardware configurations are limited in terms of satisfying operator needs and do not easily support all types of applications or content. In this work, we consider graphic < e‐Adventure > educational games, which are not directly executable on typical STBs. To cover this gap and guarantee an enjoyable user experience, we present an architecture based on a combination of streaming and remote desktop protocols that relies on virtualized servers deployed in a cloud computing infrastructure. It features an original image‐encoding signalling mechanism that identifies multimedia content in educational games and permits seamless protocol switching at the client side. This architecture is a complete technological solution to virtualize heavy educational games and execute them smoothly on STB light clients over Internet Protocol Television networks. We present performance results that show that our proposal is an efficient scalable solution to deliver t‐Learning to home environments. Copyright © 2013 John Wiley & Sons, Ltd.     

Enhancing recommender systems by incorporating social information

Although recommendation techniques have achieved distinct developments over the decades,the data sparseness problem of the involved user-item matrix still seriously influences the recommendation quality.Most of the existing techniques for recommender systems cannot easily deal with users who have very few ratings.How to combine the increasing amount of different types of social information such as user generated content and social relationships to enhance the prediction precision of the recommender systems remains a huge challenge.In this paper,based on a factor graph model,we formalize the problem in a semi-supervised probabilistic model,which can incorporate different user information,user relationships,and user-item ratings for learning to predict the unknown ratings.We evaluate the method in two different genres of datasets,Douban and Last.fm.Experiments indicate that our method outperforms several state-of-the-art recommendation algorithms.Furthermore,a distributed learning algorithm is developed to scale up the approach to real large datasets.     

PersonalTV

This paper presents an approach to build a TV recommendation system called PersonalTV that enables the use of multiple classifiers, each one specialized on selected attributes of detailed program information. For generating adequate recommendations, the system makes use of content filtering and the preferences directly specified by the user within an MPEG-7 profile. By tracking user actions and interpreting their semantics, the system is able to individually weight these actions and dynamically adjusts the process to the user’s evolving preferences. We show how specialized spam fighting methods can successfully be transferred to the area of recommendation systems and adapted accordingly. Being lightweight, these methods are especially applicable in resource-constrained environments such as TV set-top boxes or mobile devices. Moreover, the use of the variance of the beta-distribution as a confidence value for each recommendation is presented.