Haiping Zhu

A multi-constraint learning path recommendation algorithm based on knowledge map

Abstract It is difficult for e-learners to make decisions on how to learn when they are facing with a large amount of learning resources, especially when they have to balance available limited learning time and multiple learning objectives in various learning scenarios. This research presented in this paper addresses this challenge by proposing a new multi-constraint learning path recommendation algorithm based on knowledge map. The main contributions of the paper are as follows. Firstly, two hypotheses on e-learners’ different learning path preferences for four different learning scenarios (initial learning, usual review, pre-exam learning and pre-exam review) are verified through questionnaire-based statistical analysis. Secondly, according to learning behavior characteristics of four types of the learning scenarios, a multi-constraint learning path recommendation model is proposed, in which the variables and their weighted coefficients considers different learning path preferences of the learners in different learning scenarios as well as learning resource organization and fragmented time. Thirdly, based on the proposed model and knowledge map, the design and implementation of a multi-constraint learning path recommendation algorithm is described. Finally, it is shown that the questionnaire results from over 110 e-learners verify the effectiveness of the proposed algorithm and show the similarity between the learners’ self-organized learning paths and the recommended learning paths.

Design and prototype implementation of social value evaluation system for voluntary service

Evaluating the social value of voluntary service (especially the quality of collaborative service) not only measures the degree of society civilization, but also provides the guidance or indicator of overall arrangement of voluntary service and utilization efficiency of voluntary resources. Along with the informatization development of the network, the release, implementation and evaluation of voluntary service can be integrated into a management information system. Unfortunately, the current research seldom involves comprehensive evaluation system, especially one considering the indicator of collaboration. This paper proposes a Social Value Evaluation System for Voluntary Service (SVESVS) and also presents design and implementation of prototype of the evaluation system. Based on simulated data and data obtained from national volunteer service platform, the proposed evaluation system is tested, visualized and validated from different dimensions. With the help of this information management system, the process tracking, monitoring and the resource integration of volunteer service can be achieved effectively.

A Semantic Relevancy Measure Algorithm of Chinese Sentences

The semantic relevancy measures between sentences play an increasingly important role in text-related research and applications in areas such as text categorization, text-reasoning, text structure analysis and Question-Answering system. In this paper, focusing on the Chinese short text, a novel semantic relevancy measure algorithm between sentences is proposed. This method calculates sentence relevancy by combining the word-form feature, semantic feature and syntax feature in sentences. Besides semantic feature, the syntax structure information of sentences is also considered. Experiments prove that the proposed algorithm is efficient and useful in semantic relevancy measure of Chinese sentence.

Identification and extraction of topic elements for Chinese interactive text

This paper is based on identification and extraction of topic elements for Chinese interactive text. A topic segmentation method based on time sequence is achieved. Then a novel identification and extraction algorithm of topic elements is proposed. Firstly, noise filtering and Chinese word segmentation on the original corpus are executed. Secondly, the identifying and extracting method in group of mixed turn is used to extract the topic elements, such as time, place and figure. Finally, performance evaluation of identification recall, identification accuracy and extraction accuracy are achieved. The experimental results show the effectiveness of the algorithm.

Chinese sentence correlation analyzing based on semantic dependency method

Based on the adoption of dependency grammar to analyze the structure of Chinese sentences, this paper suggests to analyze Chinese sentence with semantic dependency method. The correlation between words and phrases can be gotten by way of analysis and calculation of the similarity between the words and phrases from Hownet, and then the formula to analyze the similarity between sentences can be designed. Fully considering the relationship between structure and semantics of Chinese sentences, this methodology can be adopted to analyze the correlation between topics and to categorize them. It has certain prospect in the field of Chinese language research, personalized online education and recommendation of resources for the users.

A Topic Partition Algorithm Based on Average Sentence Similarity for Interactive Text

Based on the research and analysis of interactive text properties, the word frequency statistics and synonyms merger are imported to obtain the keywords of interactive text. The Sentence similarity is used to describe the degree of coupling between sentences. Then a novel topic partition algorithm based on average sentence similarity is proposed. The experimental results show the effectiveness of the algorithm. Along with the mining of the deep correlations among texts, the algorithm precision and accuracy will be improved.