Jaechoon Jo

Developing a hybrid collaborative filtering recommendation system with opinion mining on purchase review

The most commonly used algorithm in recommendation systems is collaborative filtering. However, despite its wide use, the prediction accuracy of this algorithm is unexceptional. Furthermore, whether quantitative data such as product rating or purchase history reflect users’ actual taste is questionable. In this article, we propose a method to utilise user review data extracted with opinion mining for product recommendation systems. To evaluate the proposed method, we perform product recommendation test on Amazon product data, with and without the additional opinion mining result on Amazon purchase review data. The performances of these two variants are compared by means of precision, recall, true positive recommendation (TPR) and false positive recommendation (FPR). In this comparison, a large improvement in prediction accuracy was observed when the opinion mining data were taken into account. Based on these results, we answer two main questions: ‘Why is collaborative filtering algorithm not effective?’ and ‘Do quantitative data such as product rating or purchase history reflect users’ actual tastes?’

A Method for Measuring Cooperative Activities in a Social Network Supported Learning Environment

Cooperative learning, which can foster an active learner-oriented learning environment and induce active interaction among students, is an important element that can enhance the effects of learning in the online learning environment as well. As most existing studies on cooperative learning are based only on a qualitative evaluation in the offline environment, however, it is difficult to measure cooperative learning in the online learning environment. Thus, for this study a group cooperative activity (GCA) was proposed to quantitatively measure the cooperative learning of learners in the online learning environment, and a social network analysis (SNA) method was used to visualize the cooperative activities among the learners. The result of the experiment shows that the GCA among teachers was higher than the GCA among learners in the Formal Learning Group, whereas many high-density network models were observed in the Non-Formal Learning Group and the GCA among learners was higher. The proposed GCA uses the interaction data generated among the learner group to measure its cooperative learning. Also, this study verified the effectiveness of the GCA by using an SNA for visualization purposes.

Mining students activities from a computer supported collaborative learning system based on peer to peer network

As Information & Communication Technology (ICT) is rapidly evolved, educational paradigms have been changing. The ultimate goal of education with the aid of ICT is to provide customized training for learners to improve the effectiveness of their learning at anytime and anywhere. In the online learning environment where the Internet, mobile devices, peer-to-peer (P2P) and the cloud technology are leveraged, all the information in learning activities is converted into digital data and stored in the Computer Supported Collaborative Learning (CSCL) system. The data in the CSCL system contains various learners’ information including the learning objectives, learning preferences, competences and achievements. Thus, by analyzing the activity information of learners in an online CSCL system, meaningful and useful information can be extracted and provided for learners, teachers and administrators as feedback. In this paper, we propose a learner activity model that represents the learner’s activity information stored in a CSCL system. As for the proposed learner activity model, we classified the learning activities in a CSCL system into three categories: vivacity, learning and relationship; then we created quotients to represent them accordingly. In addition, we developed a CSCL System, which we termed as COLLA, applied the proposed learner activity model and analyzed the results.

Comparative Analysis of Learning Effect on Lexical Recognition in the e-Learning and s-Learning

The purpose of this study is to analyze learning effects of e-learning and s-learning on learner’s brain. The subjects of this study were twenty elementary school students. The experimental group was divided into two groups and both groups learned the same content. As a result of the research, both groups showed improvement. But s-learning is higher than e-learning in the effect of learning based on the brain.

Development of a Game-Based Learning Judgment System for Online Education Environments Based on Video Lecture: Minimum Learning Judgment System:

We propose a minimum learning judgment system that is appropriate for online learning environments, and we verify this minimum learning judgment system through various experiments. By focusing on the learning effort, this system can easily and quickly determine whether learners have exerted the minimum effort required for learning. To do this, the system automatically generates a word game and determines whether minimum learning has taken place through the results of the word game. To verify the minimum learning judgment system, we conducted a comparative experiment on the importance of high-frequency words, a word count verification test for word games, and a judgment criteria verification test based on the length of a video lecture. Results of the experiments show that high-frequency words can be used as a feature to determine minimum learning. The appropriate number of words in the word game for the minimum learning judgment was found to be seven, and the results showed that the video length did not affect the minimum learning criteria. In addition, the minimum learning judgment accuracy result was 82%. This is not considered very high judgment accuracy, but the accuracy of the judgment is positive considering the aim of this study.

A comparative study on gamification of the flipped classroom in engineering education to enhance the effects of learning

This study analyzes the effectiveness of adding educational gaming elements into the online lecture system of the flipped classroom as a method to increase participation and interest in online preparation before class. This study held an “understanding sequence” for 20 classes during the 7‐week automation equipment class with 30 s year high school students in Incheons specialized technical high school as target. After the class, the learning attitude of learners was measured through surveys and in‐depth interviews. As a result, first, it was found that the degree of preparation participation in flip learning using gaming elements had a statistically significant increase from 65.56% to 78.89%, compared with the traditional flip learning using YouTube. Second, comparing the academic achievements showed a diagnostic assessment of 57.44 before applying the gaming elements and 20.17 after the application. However, for summative assessment, the degree after applying gaming elements was statistically higher at 84.52 than the degree before application, which was 78.86. Third, comparing academic achievement with word game results showed no significant correlation, and it is judged that all students were able to enjoy word games, regardless of their grades. Also, when the average word game scores were compared based on students’ grades, mid‐upper level students had statistically significant higher scores than upper level students. Lastly, analysis on the correlation between attitude and word game showed that there is a quantitatively high correlation between the ranking systems competitive spirit and interest. The ranking system increased competitive spirit, as well as interest.

A Study of Keywords Based on the Word Frequency Effect Theory in Video Lectures of Software Engineering Education for Detecting Mind

The increased popularity of Massive Open Online Courses (MOOC) and e-learning has constantly increased video-based online education platforms. There are also many video lectures for software engineering education in online education platforms. Although online lectures have many advantages, there are also limitations. We performed a verification research to see if high frequency words can detect mind wandering to resolve existing limitations. In this verification study, experiments to identify whether high frequency words can represent the software engineering video lecture, the minimum number of words needed to detect mind wandering, and whether mind wandering detection standards should be changed according to the length of the video lecture. The results of this study confirmed that mind wandering can be detected through high frequency words and they can be used as an important feature in various learning analysis investigations to resolve existing limitations of online education.

User Sentiment Analysis on Amazon Fashion Product Review Using Word Embedding

In the modern society, the size of the fashion market is continuously increasing both overseas and domestic. When purchasing a product through e-commerce, the evaluation data for the product created by other consumers has an effect on the consumers decision to purchase the product. By analysing the consumer’s evaluation data on the product the company can reflect consumer’s opinion which can leads to positive affect of performance to company. In this paper, we propose a method to construct a model to analyze user s sentiment using word embedding space formed by learning review data of amazon fashion products. Experiments were conducted by learning three SVM classifiers according to the number of positive and negative review data using the formed word embedding space which is formed by learning 5.7 million Amazon review data.. Experimental results showed the highest accuracy of 88.0% when learning SVM classifier using 50,000 positive review data and 50,000 negative review data. •

Design of a Structured Plug-in Smart Education System

With a recent emergence and growing interest in smart education and rapid growth of the related market, we established Structured Plug-in Smart Education System for effective smart education, based on the concept of smart education, research, and technology. This system consists of a Smart Contents Service System that links learning contents to producing, managing, and learning, as well as a School and Home Learning System that supports cooperating, intellectual, and life-long learning by creating learning spaces in school and home, and effective learning correlation. In order to realize this system for smart education, we plan to verify the effectiveness of the Structured Plug-in Smart Education System by applying this system to formal education and analyzing its effectiveness.