• Journal of The Korean Association For Science Education
• /
• v.43 no.1
• /
• pp.17-28
• /
• 2023

In line with the entry into the digital-based intelligent information society, the science curriculum emphasizes the cultivation of scientific competencies, and computer-based test (CBT) is drawing attention for assessment of competencies. CBT has advantages to develop items that have high fidelity, and to establish a feedback system by accumulating results into the database. However, it is necessary to solve the problems of improving validity of assessment results, lowering measurement efficiency, and increasing management factors. To examine students' responses to the introduction of the new assessment tools in the process of transitioning from paper-based test (PBT) to CBT, in this study, we analyzed the results of the PBT and the CBT conducted in 2021 National Assessment of Educational Achievement (NAEA). In particular, we sought to find the effects on student achievement when only the mode of assessment was changed without change of items, and the effect on student achievement when the items were composed including technology enhanced features that take advantage of CBT. This study is derived through the analysis of the results of 7,137 third-grade middle school students taking one among the three kinds of assessments, which were the PBT or two kinds of CBT. After the assessment, the percentage of correct answers and the item discriminations were collected for each group, and expert opinions on characteristics of response were collected through the expert council involving 8 science teachers with experience in NAEA. According to the results, there was no significant difference between students' achievement results in the PBT and the CBT-M, which means simple mode conversion type of CBT, so it could be explained that the mode effect did not appear. However, it was confirmed that the percentage of correct answers for the construct response items was somewhat high in the CBT, and this result was analyzed to be related to the convenience of the response. On the other hand, there were the items with a difference of more than 10%p from the correct answer rate of similar items, among the items to which technology enhanced functions were applied following the introduction of CBT. According to the analysis of response rate of options, these results could be explained that the students' level of understanding could be more closely grasped through the innovative items developed through the technology enhanced function. Based on the results, we discussed some guidance to be considered when introducing CBT and developing items through CBT, and presented implications.

• Journal of Intelligence and Information Systems
• /
• v.29 no.3
• /
• pp.1-17
• /
• 2023

With the recent rapid development of ICT(Information and Communication Technology) and the popularization of digital devices, the size of the online market continues to grow. As a result, we live in a flood of information. Thus, customers are facing information overload problems that require a lot of time and money to select products. Therefore, a personalized recommender system has become an essential methodology to address such issues. Collaborative Filtering(CF) is the most widely used recommender system. Traditional recommender systems mainly utilize quantitative data such as rating values, resulting in poor recommendation accuracy. Quantitative data cannot fully reflect the user's preference. To solve such a problem, studies that reflect qualitative data, such as review contents, are being actively conducted these days. To quantify user review contents, text mining was used in this study. The general CF consists of the following three steps: user-item matrix generation, Top-N neighborhood group search, and Top-K recommendation list generation. In this study, we propose a recommendation algorithm that applies an extended similarity measure, which utilize quantified review contents in addition to user rating values. After calculating review similarity by applying TF-IDF, Word2Vec, and Doc2Vec techniques to review content, extended similarity is created by combining user rating similarity and quantified review contents. To verify this, we used user ratings and review data from the e-commerce site Amazon's "Health and Personal Care". The proposed recommendation model using extended similarity measure showed superior performance to the traditional recommendation model using only user rating value-based similarity measure. In addition, among the various text mining techniques, the similarity obtained using the TF-IDF technique showed the best performance when used in the neighbor group search and recommendation list generation step.

• Journal of Intelligence and Information Systems
• /
• v.26 no.1
• /
• pp.97-117
• /
• 2020

Product evaluation criteria is an indicator describing attributes or values of products, which enable users or manufacturers measure and understand the products. When companies analyze their products or compare them with competitors, appropriate criteria must be selected for objective evaluation. The criteria should show the features of products that consumers considered when they purchased, used and evaluated the products. However, current evaluation criteria do not reflect different consumers' opinion from product to product. Previous studies tried to used online reviews from e-commerce sites that reflect consumer opinions to extract the features and topics of products and use them as evaluation criteria. However, there is still a limit that they produce irrelevant criteria to products due to extracted or improper words are not refined. To overcome this limitation, this research suggests LDA-k-NN model which extracts possible criteria words from online reviews by using LDA and refines them with k-nearest neighbor. Proposed approach starts with preparation phase, which is constructed with 6 steps. At first, it collects review data from e-commerce websites. Most e-commerce websites classify their selling items by high-level, middle-level, and low-level categories. Review data for preparation phase are gathered from each middle-level category and collapsed later, which is to present single high-level category. Next, nouns, adjectives, adverbs, and verbs are extracted from reviews by getting part of speech information using morpheme analysis module. After preprocessing, words per each topic from review are shown with LDA and only nouns in topic words are chosen as potential words for criteria. Then, words are tagged based on possibility of criteria for each middle-level category. Next, every tagged word is vectorized by pre-trained word embedding model. Finally, k-nearest neighbor case-based approach is used to classify each word with tags. After setting up preparation phase, criteria extraction phase is conducted with low-level categories. This phase starts with crawling reviews in the corresponding low-level category. Same preprocessing as preparation phase is conducted using morpheme analysis module and LDA. Possible criteria words are extracted by getting nouns from the data and vectorized by pre-trained word embedding model. Finally, evaluation criteria are extracted by refining possible criteria words using k-nearest neighbor approach and reference proportion of each word in the words set. To evaluate the performance of the proposed model, an experiment was conducted with review on '11st', one of the biggest e-commerce companies in Korea. Review data were from 'Electronics/Digital' section, one of high-level categories in 11st. For performance evaluation of suggested model, three other models were used for comparing with the suggested model; actual criteria of 11st, a model that extracts nouns by morpheme analysis module and refines them according to word frequency, and a model that extracts nouns from LDA topics and refines them by word frequency. The performance evaluation was set to predict evaluation criteria of 10 low-level categories with the suggested model and 3 models above. Criteria words extracted from each model were combined into a single words set and it was used for survey questionnaires. In the survey, respondents chose every item they consider as appropriate criteria for each category. Each model got its score when chosen words were extracted from that model. The suggested model had higher scores than other models in 8 out of 10 low-level categories. By conducting paired t-tests on scores of each model, we confirmed that the suggested model shows better performance in 26 tests out of 30. In addition, the suggested model was the best model in terms of accuracy. This research proposes evaluation criteria extracting method that combines topic extraction using LDA and refinement with k-nearest neighbor approach. This method overcomes the limits of previous dictionary-based models and frequency-based refinement models. This study can contribute to improve review analysis for deriving business insights in e-commerce market.

• Journal of Wetlands Research
• /
• v.25 no.1
• /
• pp.35-47
• /
• 2023

Korean facility horticulture and hydroponic cultivation methods increase, requiring the management of waste water generated. In this study, the amount of fertilizer contained in the discharged waste liquid was determined. By evaluating this as a price, it was suggested to reduce water treatment costs and recycle fertilizer components. It was evaluated based on the results of major water quality analysis of waste liquid by crop, such as tomatoes, paprika, cucumbers, and strawberries, and in the case of P component, it was analyzed by converting it to the amount of phosphoric acid (P₂O₅). The amount of nitrogen (N) can be calculated by discharging 1,145.90kg·ha^-1 of tomatoes, 920.43kg·ha^-1 of paprika, 804.16kg·ha^-1 of cucumbers, 405.83kg·ha^-1 of strawberries, and the fertilizer content of P₂O₅ is 830.65kg·ha^-1 of paprika, 622.32kg·ha^-1 of tomatoes, 477.67kg·ha^-1 of cucumbers. In addition, trace elements such as potassium (K), calcium (Ca), magnesium (Mg), iron (Fe), and manganese (Mn) were also analyzed to be emitted. The price per kg of each item calculated by averaging the price of fertilizer sold on the market can be evaluated as KRW, N 860.7, P 2,378.2, K 2,121.7, Ca 981.2, Mg 1,036.3, Fe 126,076.9, Mn 62,322.1, Zn 15,825.0, Cu 31,362.0, B 4,238.0, Mo 149,041.7. The annual fertilizer loss amount for each crop was calculated by comprehensively considering the price per kg calculated based on the market price of fertilizer, the concentration of waste by crop analyzed earlier, and the average annual emission of hydroponic cultivation. As a result of the analysis, the average of the four hydroponic crops was 5,475,361.1 won in fertilizer ingredients, with tomatoes valued at 6,995,622.3 won, paprika valued at 7,384,923.8 won, cucumbers valued at 5,091,607.9 won, and strawberries valued at 2,429,290.6 won. It was expected that if hydroponic drainage is managed through self-treatment or threshing before discharge rather than by leaking it into a river and treating it as a pollutant, it can be a valuable reusable fertilizer ingredient along with reducing water treatment costs.