To promote information service ability of digital libraries, a browsing and searching personalized recommendation framework based on the use of ontology is described, where the advantages of ontology are exploited in ...To promote information service ability of digital libraries, a browsing and searching personalized recommendation framework based on the use of ontology is described, where the advantages of ontology are exploited in different parts of the retrieval cycle including query-based relevance measures, semantic user preference representation and automatic update, and personalized result ranking. Both the usage and information resources can be exploited to extract useful knowledge from the way users interact with a digital library. Through combination and mapping between the extracted knowledge and domain ontology, semantic content retrieval between queries and documents can be utilized. Furthermore, ontology-based conceptual vector of user preference can be applied in personalized recommendation feedback.展开更多
Over the years, there has been increasing growth in academic digital libraries. It has therefore become overwhelming for researchers to determine important research materials. In most existing research works that cons...Over the years, there has been increasing growth in academic digital libraries. It has therefore become overwhelming for researchers to determine important research materials. In most existing research works that consider scholarly paper recommendation, the researcher’s preference is left out. In this paper, therefore, Frequent Pattern (FP) Growth Algorithm is employed on potential papers generated from the researcher’s preferences to create a list of ranked papers based on citation features. The purpose is to provide a recommender system that is user oriented. A walk through algorithm is implemented to generate all possible frequent patterns from the FP-tree after which an output of ordered recommended papers combining subjective and objective factors of the researchers is produced. Experimental results with a scholarly paper recommendation dataset show that the proposed method is very promising, as it outperforms recommendation baselines as measured with nDCG and MRR.展开更多
User profiles representing users’preferences and interests play an important role in many applications of personalized recommendation.With the rapid growth of social platforms,there is a critical need for efficient s...User profiles representing users’preferences and interests play an important role in many applications of personalized recommendation.With the rapid growth of social platforms,there is a critical need for efficient solutions to learn user profiles from the information they shared on social platforms so as to improve the quality of recommendation services.The problem of user profile learning is significantly challenging due to difficulty in handling data from multiple sources,in different formats and often associated with uncertainty.In this paper,we introduce an integrated approach that combines advanced Machine Learning techniques with evidential reasoning based on Dempster-Shafer theory of evidence for user profiling and recommendation.The developed methods for user profile learning and multi-criteria collaborative filtering are demonstrated with experimental results and analysis that show the effectiveness and practicality of the integrated approach.A proposal for extending multi-criteria recommendation systems by incorporating user profiles learned from different sources of data into the recommendation process so as to provide better recommendation capabilities is also highlighted.展开更多
近年来,随着移动定位技术的发展和位置社交网络的日益普及,基于位置社交网络(Location Based Social Network,LBSN)的位置推荐技术越来越受到人们的关注和重视,并在旅游推荐、位置导航、广告推送等领域有着广泛的应用.目前大多数基于位...近年来,随着移动定位技术的发展和位置社交网络的日益普及,基于位置社交网络(Location Based Social Network,LBSN)的位置推荐技术越来越受到人们的关注和重视,并在旅游推荐、位置导航、广告推送等领域有着广泛的应用.目前大多数基于位置社交网络的位置推荐方法在用户偏好提取的过程中考虑因素过于单一,导致用户偏好提取不准确,而且未充分考虑社交网络中的用户间信任关系,造成推荐准确率不高.针对此问题,本文设计了特殊的用户偏好存储结构——分类层次偏好树来更加准确地提取个人偏好.在此过程中,本文充分考虑了习惯性偏好、偶然性偏好以及时间因素对用户偏好的影响,使用户偏好提取更加准确,同时,结合位置社交网络中的用户信任关系来进行位置推荐.实验结果表明,本文提出的位置推荐方法得到了较高的推荐准确率.展开更多
基金The Young Teachers Scientific Research Foundation(YTSRF) of Nanjing University of Science and Technology in the Year of2005-2006.
文摘To promote information service ability of digital libraries, a browsing and searching personalized recommendation framework based on the use of ontology is described, where the advantages of ontology are exploited in different parts of the retrieval cycle including query-based relevance measures, semantic user preference representation and automatic update, and personalized result ranking. Both the usage and information resources can be exploited to extract useful knowledge from the way users interact with a digital library. Through combination and mapping between the extracted knowledge and domain ontology, semantic content retrieval between queries and documents can be utilized. Furthermore, ontology-based conceptual vector of user preference can be applied in personalized recommendation feedback.
文摘Over the years, there has been increasing growth in academic digital libraries. It has therefore become overwhelming for researchers to determine important research materials. In most existing research works that consider scholarly paper recommendation, the researcher’s preference is left out. In this paper, therefore, Frequent Pattern (FP) Growth Algorithm is employed on potential papers generated from the researcher’s preferences to create a list of ranked papers based on citation features. The purpose is to provide a recommender system that is user oriented. A walk through algorithm is implemented to generate all possible frequent patterns from the FP-tree after which an output of ordered recommended papers combining subjective and objective factors of the researchers is produced. Experimental results with a scholarly paper recommendation dataset show that the proposed method is very promising, as it outperforms recommendation baselines as measured with nDCG and MRR.
基金This work is supported by the University of Information Technology-Vietnam National University Ho Chi Minh City under grant No.D1-2023-10.
文摘User profiles representing users’preferences and interests play an important role in many applications of personalized recommendation.With the rapid growth of social platforms,there is a critical need for efficient solutions to learn user profiles from the information they shared on social platforms so as to improve the quality of recommendation services.The problem of user profile learning is significantly challenging due to difficulty in handling data from multiple sources,in different formats and often associated with uncertainty.In this paper,we introduce an integrated approach that combines advanced Machine Learning techniques with evidential reasoning based on Dempster-Shafer theory of evidence for user profiling and recommendation.The developed methods for user profile learning and multi-criteria collaborative filtering are demonstrated with experimental results and analysis that show the effectiveness and practicality of the integrated approach.A proposal for extending multi-criteria recommendation systems by incorporating user profiles learned from different sources of data into the recommendation process so as to provide better recommendation capabilities is also highlighted.
文摘近年来,随着移动定位技术的发展和位置社交网络的日益普及,基于位置社交网络(Location Based Social Network,LBSN)的位置推荐技术越来越受到人们的关注和重视,并在旅游推荐、位置导航、广告推送等领域有着广泛的应用.目前大多数基于位置社交网络的位置推荐方法在用户偏好提取的过程中考虑因素过于单一,导致用户偏好提取不准确,而且未充分考虑社交网络中的用户间信任关系,造成推荐准确率不高.针对此问题,本文设计了特殊的用户偏好存储结构——分类层次偏好树来更加准确地提取个人偏好.在此过程中,本文充分考虑了习惯性偏好、偶然性偏好以及时间因素对用户偏好的影响,使用户偏好提取更加准确,同时,结合位置社交网络中的用户信任关系来进行位置推荐.实验结果表明,本文提出的位置推荐方法得到了较高的推荐准确率.
