• Journal of the Korea Academia-Industrial cooperation Society
• /
• v.10 no.10
• /
• pp.2893-2899
• /
• 2009

The study classified speech styles of shopping hosts and tried to examine how the classified speech styles have an effect on the evaluation of shopping hosts and the purchase intentions. In the evaluation of speech styles of shopping hosts, except customer-oriented confutative style, credibility, descriptive relevance, other speech styles are analyzed to have an impact on the styles. When we investigate the influential relations between speech styles proved by a theory and the evaluation of shopping hosts, the demonstrative style comes first, the expressive style is next and the descriptive follows in terms of influential power. In terms of the purchasing intention, speech styles of shopping hosts have an effect on the demonstrative and expressive types rather than the elucidative and descriptive ones. Namely, the analysis shows that the speech style which is logically persuasive and expresses the contents in detail is preferred to the descriptive and leading speech style.

• Journal of The Korean Association For Science Education
• /
• v.36 no.3
• /
• pp.389-397
• /
• 2016

This study aims to test the efficacy of English-based automated computer scoring models and machine translation to score Korean college students' written responses on natural selection concept items. To this end, I collected 128 pre-service biology teachers' written responses on four-item instrument (total 512 written responses). The machine translation software (i.e., Google Translate) translated both original responses and spell-corrected responses. The presence/absence of five scientific ideas and three $na{\ddot{i}}ve$ ideas in both translated responses were judged by the automated computer scoring models (i.e., EvoGrader). The computer-scored results (4096 predictions) were compared with expert-scored results. The results illustrated that no significant differences in both average scores and statistical results using average scores was found between the computer-scored result and experts-scored result. The Pearson correlation coefficients of composite scores for each student between computer scoring and experts scoring were 0.848 for scientific ideas and 0.776 for $na{\ddot{i}}ve$ ideas. The inter-rater reliability indices (Cohen kappa) between computer scoring and experts scoring for linguistically simple concepts (e.g., variation, competition, and limited resources) were over 0.8. These findings reveal that the English-based automated computer scoring models and machine translation can be a promising method in scoring Korean college students' written responses on natural selection concept items.

• The Mathematical Education
• /
• v.47 no.4
• /
• pp.487-503
• /
• 2008

In this paper, descriptive assessment method for middle school mathematics was evaluated by developing a framework for designing and grading problems for descriptive assessment and analyzing the effectiveness of the problems. The new descriptive assessment problems were developed by reviewing the current 7th National Mathematics Curriculum of Korea and aligned mathematics textbooks to define a set of problem design principles and evaluation framework for the assessment strategy. The developed problems were first pilot tested and then revised based on the feedback from the test. The final version was field tested by 100 students in 7th grade middle school. After the field test, the problems were graded by two middle school math teachers and one math education researcher to determine the overall correlation between graders and also to analyze effectiveness of the evaluation framework of the test. This result of this study is expected to assist in the further development of descriptive problems and grading framework by providing a reference work for teachers to better understand the process and the limitations of executing the new assessment strategy.

• Journal of the Korean School Mathematics Society
• /
• v.17 no.3
• /
• pp.409-435
• /
• 2014

This study examines relations between the 5th graders' fraction operation skills and error types on constructed-response items. As results, first, the participants have lower fraction operation skills on 'multiplication of fraction' than 'addition and subtraction of fraction'. Second, the participants have different error types depend on their constructed-response items. Most of error types which group with high ability made was 'leap of solving process', both groups error type with medium ability as well as low ability is 'misunderstanding of questions'. Third, the operation skills on 'addition and subtraction of fraction' have an influence on their operation skills on 'multiplication of fraction', and error types of 'understanding of questions' and 'understanding of solving process' have the most effects on the influence.

• Journal of Educational Research in Mathematics
• /
• v.23 no.3
• /
• pp.389-406
• /
• 2013

The purpose of this study is to analyze eighth grade students' errors in the constructed-response items to improve teaching and learning of mathematics in schools. By analyzing 99 students' responses to nine constructed-response items, we found several types of students' errors in their responses to the assessment items involving with mathematical reasoning and representations, problems within realistic contexts, and mathematical connections. Not only a single error but also multiple errors (a combination of two or more types of errors) were discovered. In particular, high achieving students showed more simple errors than multiple errors while low achieving students had more multiple errors in various kinds.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2009.10a
• /
• pp.595-598
• /
• 2009

최근 영재 및 영재교육에 관련된 연구가 다방면에서 진행되고 있으며, 초기에 수학 및 과학 분야 위주로 이루어졌던 영재교육은 정보, 발명, 인문, 예술 등의 기타 분야로 점차 확대되어 가고 있다. 사회적으로는 고도화된 정보화 사회로의 진행과 더불어 정보과학에서도 영재교육데 대한 관심과 중요성이 커지고 있다. 그러나 정보과학의 학문적 역사가 짧고 그 범위의 설정이 어려운 만큼 정보과학 분야의 영재교육에 있어서도 대상자의 선발과 교육이 어려운 것이 사실이다. 특히 영재교육 대상자의 선정과 교육에 필수적인 평가 방식에 대한 학문적 연구가 부족하여 교육 방식의 보완과 창의적인 대상자 선발에 있어 개선에 대한 목소리가 높다. 이에 본 연구에서는 여러 형태의 평가 방식 중 관찰평가가 평가도구로서 어떻게 작용하는지 다면 평가의 측면에서 지필평가와 보완적 작용을 하는지에 대해 연구하였다. 이를 위해 2년간의 학습자들의 지필평가 성적과 관찰평가 중 리커트 척도 방식의 체크리스트와 서술형 관찰 기록지 사이의 상관관계를 통계적으로 분석 하였다. 또한 항목간의 상관관계를 알아보기 위해 체크리스트와 서술형 관찰기록지의 하위 항목간의 상관관계를 분석하였다. 연구 결과 체크리스트의 하위항목 분석을 통해서는 태도와 문제해결 능력 간의 상관관계, 수학적인지영역과 문제해결 능력 간의 유의미한 상관 관계를 알 수 있었으며, 서술형 관찰 기록지 분석을 통해서는 투입 프로그램 적응 능력이라 할 수 있는 과정적 영역은 정의적 영역과 인지적 영역의 상관 관계가 중요함을 알 수 있었다. 또한 평가 방식간의 상관 관계는 지필 평가와 관찰 평가의 유의미한 연관성이 없다는 것이 밝혀졌다. 즉, 정보과학 분야 영재교육 학습자의 잠재 능력이나 사회성, 창의성, 문제해결력 등을 평가하기 위해서는 지필평가와 더불어 관찰평가가 반드시 필요하며 다면평가의 측면에서 상호 보완적인 역할을 한다는 것이다.

• The Mathematical Education
• /
• v.63 no.2
• /
• pp.165-186
• /
• 2024

Despite the growing attention on artificial intelligence-based automated scoring technology as a support method for the introduction of descriptive items in school environments and large-scale assessments, there is a noticeable lack of foundational research in mathematics compared to other subjects. This study developed an automated scoring model for two descriptive items in first-year middle school mathematics using the Random Forest algorithm, evaluated its performance, and explored ways to enhance this performance. The accuracy of the final models for the two items was found to be between 0.95 to 1.00 and 0.73 to 0.89, respectively, which is relatively high compared to automated scoring models in other subjects. We discovered that the strategic selection of the number of evaluation categories, taking into account the amount of data, is crucial for the effective development and performance of automated scoring models. Additionally, text preprocessing by mathematics education experts proved effective in improving both the performance and interpretability of the automated scoring model. Selecting a vectorization method that matches the characteristics of the items and data was identified as one way to enhance model performance. Furthermore, we confirmed that oversampling is a useful method to supplement performance in situations where practical limitations hinder balanced data collection. To enhance educational utility, further research is needed on how to utilize feature importance derived from the Random Forest-based automated scoring model to generate useful information for teaching and learning, such as feedback. This study is significant as foundational research in the field of mathematics descriptive automatic scoring, and there is a need for various subsequent studies through close collaboration between AI experts and math education experts.

• The Journal of Korean Association of Computer Education
• /
• v.21 no.6
• /
• pp.105-115
• /
• 2018

The descriptive-type question is appropriate for deep thinking ability evaluation, but it is not easy to grade. Since, even though same grading criterion, the graders produce different scores, we need the objective evaluation system. However, the system needs the Korean analysis. As the descriptive-type answering is described with the compound sentence, the system has to analyze the compound sentence. This paper develops the Korean syntactic-semantic analysis system for compound sentence and evaluates performance of the system. This system selects the modifiee of the word phrase using syntactic-semantic constraint and semantic dictionary. The 93% accurate rate shows that the system is effective. This system will be utilized in descriptive-type grading and Korean processing.

• The Mathematical Education
• /
• v.46 no.2 s.117
• /
• pp.207-226
• /
• 2007

The purpose of this study was to design and develop the processes of tasks and assessment rubrics of open-ended tasks, and those for the 5th graders of elementary school mathematics. 7 tasks were finally developed, and 'problem understanding', 'problem solving process', 'communication' were selected as the criteria for assessment rubrics. The result was that the ability of mathematical power covering problem understanding ability, problem solving ability and mathematical communication ability was low. Specifically, problem understanding ability was the highest, problem solving ability was middle, and mathematical communication ability was the lowest.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2023.11a
• /
• pp.23-26
• /
• 2023

본 논문에서는 서술형 수학 문제 풀이 모델의 숫자 대소관계 파악을 위한 명시적 자질추출방식 Explicit Feature Extraction(EFE) Reasoner 모델을 제안한다. 서술형 수학 문제는 자연현상이나 일상에서 벌어지는 사건을 수학적으로 기술한 문제이다. 서술형 수학 문제 풀이를 위해서는 인공지능 모델이 문장에 함축된 논리를 파악하여 수식 또는 답을 도출해야 한다. 때문에 서술형 수학 문제 데이터셋은 인공지능 모델의 언어 이해 및 추론 능력을 평가하는 지표로 활용되고 있다. 기존 연구에서는 문제를 이해할 때 숫자의 대소관계를 파악하지 않고 문제에 등장하는 변수의 논리적인 관계만을 사용하여 수식을 도출한다는 한계점이 존재했다. 본 논문에서는 자연어 이해계열 모델 중 SVAMP 데이터셋에서 가장 높은 성능을 내고 있는 Deductive-Reasoner 모델에 숫자의 대소관계를 파악할 수 있는 방법론인 EFE 를 적용했을 때 RoBERTa-base 에서 1.1%, RoBERTa-large 에서 2.8%의 성능 향상을 얻었다. 이 결과를 통해 자연어 이해 모델이 숫자의 대소관계를 이해하는 것이 정답률 향상에 기여할 수 있음을 확인한다.