Web-Based Learning Object Search Engine Solution Together with Data Visualization: The Case of MERLOT II

Gunarathne, W. K. T. M.; Chootong, Chalothon; Sommool, Worapot; Ochirbat, Ankhtuya; Chen, Yi-Cheng; Reisman, Sorel; Shih, Timothy K.

doi:10.1109/compsac.2018.00179

Cited by 6 publications

(2 citation statements)

References 19 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In general, there may be parent-child relationship between topics, that is, the parent topic has a more general discussion topic, and the child topic has a more detailed discussion topic. Using the hierarchical tree approach to clearly present the parent-child relationship between query topics is especially useful for poor or ambiguous queries [8], [9]. To present the relationship, the system uses the operations of the sets to calculate possible inclusion relationships between topics.…”

Section: B Research Ideas For This Studymentioning

confidence: 99%

A Study of Optimizing Search Engine Results Through User Interaction

Chen

2020

IEEE Access

View full text Add to dashboard Cite

In this paper, we propose a method for optimizing search engine results based on user interaction. This method generates different search results mainly through the user's operation on different search topics. There are two main differences between our method and the traditional personalized search method: personal privacy and storage space. First, traditional personal search methods need to record search and click records for individual users. However, these records have great personal privacy issues for users; especially in recent years, there have been personal privacy leaks that occurred in many large online companies (such as Facebook and Yahoo). Secondly, because different users need to record their own search records, the size of the storage space is closely related to the number of users and the amount of search records stored. However, the sum of individual users' search and click records is a huge storage space in today's Internet environment. To avoid these two issues for traditional personalized search methods, this study proposes a storage-free approach based on individual users operating on different search topics. In general, in addition to avoiding personal privacy and storage space issues, our method can also achieve optimal linear time in generating personalized search results. INDEX TERMS Document clustering, machine learning, natural language processing, personalized topic search, user log.

show abstract

Section: B Research Ideas For This Studymentioning

confidence: 99%

A Study of Optimizing Search Engine Results Through User Interaction

Chen

2020

IEEE Access

View full text Add to dashboard Cite

show abstract

“…Moreover, there are studies more specific to educational purposes. For example, Gunarathne et al [51] developed a web-based LO visualization system that works on the well-known MERLOT II LOR. In this system, when users search a keyword, results are visualized using data extraction, transformation, and clustering methods.…”

Section: Introductionmentioning

confidence: 99%

Automatic and intelligent content visualization system based on deep learning and genetic algorithm

İnce

2022

Neural Comput & Applic

View full text Add to dashboard Cite

Increasing demand in distance education, e-learning, web-based learning, and other digital sectors (e.g., entertainment) has led to excessive amounts of e-content. Learning objects (LOs) are among the most important components of electronic content (e-content) and are preserved in learning object repositories (LORs). LORs produce different types of electronic content. In producing e-content, several visualization techniques are employed to attract users and ensure a better understanding of the provided information. Many of these visualization systems match images with corresponding text using methods such as semantic web, ontologies, natural language processing, statistical techniques, neural networks, and deep neural networks. Unlike these methods, in this study, an automatic and intelligent content visualization system is developed using deep learning and popular artificial intelligence techniques. The proposed system includes subsystems that segment images to panoptic image instances and use these image instances to generate new images using a genetic algorithm, an evolution-based technique that is one of the best-known artificial intelligence methods. This large-scale proposed system was used to test different amounts of LOs for various science fields. The results show that the developed system can be efficiently used to create visually enhanced content for digital use.

show abstract