附录1 英文原文
Personalized recommendation of learning material using quential pattern mining and attribute bad collaborative filtering
Abstract
Material recommender system is a significant part of e-learning systems for personalization and recommendation of appropriate materials to learners. However, in the existing recommendation algorithms, dynamic interests and multi-preference of learners and multidimensional-attribute of materials are not fully considered simul-taneously. Moreover, the algorithms can not effectively u the learner’s historical quential patterns of material accessing in recommendation. For addressing the problems and improving the accuracy and quality of recommendation, a new material recommender system framework bad on quential pattern mining and multidimensional attribute-bad collaborative filtering (CF) is propod. In the quential pattern bad approach, modified Apriori and PrefixSpan algorithms are implemented to discover latent patterns in accessing of materials and u them for recommendation. Leaner Preference Tree (LPT) is introduced to take into account multidimensional-attribute of materials, and learners’ rating and model dynamic and multi-preference of
怎么屏蔽朋友圈learners in the multidimensional attribute-bad CF ap-proach. Finally, the recommendation results of two approaches are combined using cascade, weighted and mixed methods. The propod method outperforms the previous algorithms on the classification accuracy measures and the learner’s real learning preference can be satisfied accurately according to the real-time up dated contextual information.
Keywords: Personalized recommendation ;Apriori algorithm;. Learning material ;e-learning ; Dynamic preference ; Multi-attribute
出口补贴With growth of many online learning systems, a huge amount of e-learning materials have been generated which are highly heterogeneous and in various media formats (Chen et al. 2012). Therefore, in this situation, it is quite difficult to find
suitable learning materials ba d on learner’s preference. The task of delivering personalized learning material is often framed in terms of a recommendation task in which a system recommends items to an active ur (Mobasher 2007). Therefore, recom-mender systems have been ud for e-learning environments to recommend uful materials to urs. The systems address information overload and make a personal learning environment (PLE) for urs. The motivation for any recomm
ender system is to assure an efficient u of available materials. Using this approach, we can improve a personal learning path according to pedagogical issues and available material.
In the recent years, recommender system is being deployed in more and more e-commerce entities to best expres s and accommodate customer’s interests. According to the strategies applied, they can be divided into three major categories: content-bad, collaborative, and hybrid recommendation (Adomavicius and Tuzhilin 2005). Content-bad recommendation is derived from Information Retrieval. A content-bad recommendation algorithm identifies and extracts features of items and ur and then builds a matching model for them. Recommendations are made bad on comparison of ur’s preference and item’s features. On the other hand, the main idea of collaborative filtering is grouping like-minded urs together. The systems are also called clique-bad systems. It is assumed that urs who had similar choices before will make the same lection in the future. Collaborative recommender systems give urs suggestion by obrving the neighbor of the ur. Hybrid recom-mendation mechanisms attempt to deal with some of limitation and overcome draw-backs of pure content-bad approach and pure collaborative approach by combining the two approaches.鳄鱼养殖
There are veral drawbacks when applying existing recommendation algorithms to e-learning envir
onments directly:
Since the learning process is repeatable and periodic, there are some intrinsic orders for le arning material in urs’ learning process that can prent material access patterns. This information can reflect the learner’s latent preference. But, most of existing recommendation systems don’t u this information. To imple-ment a
quential pattern bad recommendation, the new algorithms are pre-nted in this rearch.
Some of traditional recommendation algorithms only u learners’ rating for recommendation and don’t consider attributes of learners and learning materials. To model multi-preference of learner this rearch takes into account multidimensional-attribute of materials and learners’ rating matrix in the unified model.
The learners’ preferences will be changing dynamically. Therefore, to make good recommendation in time when learners’current interests are changing, a recom-mendation algorithm must trace learner behaviour to propo dynamic recom-mendation. Thus, this rearch implements a dynamic approach for producing recommendations in the multidimensional attribute-bad CF.
经学>技术方案模板
According to the described drawbacks, this paper propos a new material recom-mender system framework and relevant recommendation algorithms for e-learning environments. First, in the multidimensional attribute-bad CF recommendation approach, to reflect lear ner’s complete spectrum of interests, Leaner Preference Tree (LPT) is introduced to consider multidimensional-attributes of materials, learn-er’s rating simultaneously. Truly, Leaner Preference Tree is built bad on target learner’s historical access reco rds and multidimensional-attributes of materials. Then, a new similarity measure that can take into account the information of LPTs for calculating similarity between learners is introduced. In the quential pattern bad recommendation approach, to discover the latent patterns of accesd materials and give recommendation, the weighted association rules (Apriori algorithm) and PrefixSpan algorithm are implemented. The results of two approaches are combined to create final recommendations.
The rest of this paper is Literature survey，In Literature survey ction, the previous related works on e-learning material recommender systems are discusd.
Learning materials have grew either offline or online in educational organizations. So, it is difficult for learners to discover the most appropriate materials according to keyword arching methods. The creation of the technology for
personalized lifelong learning has been recognized as a Grand Challenge Problem by peak rearch bodies (Kay 2008). Therefore, recommender systems have been ud for e-learning environ-ments to recommend uful materials to urs. The first recommender system was developed in the mid of 1990s (Felfernig et al. 2007). Many recommendation systems in various fields such as movies, music, news, commerce and medicine have been developed but few in education field (Drachsler et al. 2007). The Overview of the recommendation strategies and techniques with their ufulness for material recom-mendation have been prented in Table 1. We briefly survey some of important works and explain the drawbacks of them that can be addresd by our propod approach.
Content bad filtering This technique suggests items similar to the ones that each ur liked in the past taking into account the object content analysis that the ur has evaluated in the past (Lops et al. 2011). As an example for e-learning application, Khribi et al. ( 2009) ud learners' recent navigation histories and similarities and dissimilarities among the contents of the learning materials for online automatic recommendations. Clustering was propod by Hammouda and Kamel ( 2006) to group learning documents bad on their topics and similarities. In fact, the existing metrics in content bad filtering only detect similarity between items that share the same attributes. Indeed, the basic process performed by a content-bad recommender consists in matching up the attribute
s of a ur profile in which preferences and interests are stored, with the attributes of a content object (item), in order to recom-mend to the ur new interesting items (Lops et al. 2011). This caus overspecialized recommendations that only include items very similar to tho the ur already knows. To avoid the overspecialization of content-bad methods, rearchers pro-pod new personalization strategies, such as collaborative filtering and hybrid approaches mixing both techniques.
Collaborative filtering Majority of rearchers ud collaborative filtering bad recommendation system. (Milicevic et al. 2010; Bobadilla et al. 2010). CF approaches ud in e-learning environments focus on the correlations among urs having similar interests (Marlin 2004; Sergio et al. 2005) and can be divided in to
完美无瑕three categories that have been shown in Table 1. The collaborative e-learning field is strongly growing (Tan et al. 2008; García et al. 2009; García et al. 2011; Wang and Liao 2011), converting this area in an important receiver of applications and generating numerous rearch papers. Collaborative filtering was ud by Soonthornphisaj et al. ( 2006) for prediction the most suitable materials for the learner. At first, the weight between all urs and the active learner is calculated by Pearson correlation. Then, the n urs that have the highest similarity to the active learner are lect
ed as the neighborhoods. Finally, using the weight combination obtained from the neighborhood, the rating prediction is calculated. Bobadilla et al. ( 2009) ud a new equation for incorporating the learners score obtained from a test into the calculations in collaborative filtering for materials prediction. Their experiment showed that the method obtained high item-prediction accuracy.
Since in the e-learning environment learning materials are in a variety of multi-media formats including text, hypertext, image, video, audio and slides, it is difficult to calculate content similarity of two items (Chen et al. 2012). In this n, urs’ preference information is a good indication for recommendation. Therefore, CF is more suitable in e-learning systems since it is completely independent of the intrinsic properties of the items being rated or recommended (Yu et al. 2011).一年总结怎么写
Regardless of its success in many application domains, collaborative filtering has two rious drawbacks. First, its applicability and quality are limited by the so-called sparsity problem, which occurs when the available data are insufficient for identifying similar urs (Cotter and Smyth 2000). Therefore, many rearches were run to alleviate sparsity problem using data mining techniques. For example, Romero et al. ( 2009) developed a specific Web mining tool for discovering suitable rules in recommender engine. Their objective was to recommend to a student the most appropriate links/WebPages to visit next. Second, it requires knowing many ur profiles in order to elaborate ac
票的英文
curate recommendations for a given ur. Therfore, in some e-learning enviroment that number of learner is low, recommendation result has not adequate accuracy.
Hybrids To overcome drawbacks of the strategies, rearchers ud hybrid
