Maximizing ANLP Evaluation

2012 ◽  
pp. 438-456
Author(s):  
Adam Renner ◽  
Philip M. McCarthy ◽  
Chutima Boonthum-Denecke ◽  
Danielle S. McNamara
Keyword(s):  
High School ◽  
High School Students ◽  
Natural Language Processing ◽  
Language Processing ◽  
Learning Systems ◽  
School Students ◽  
Computational Approaches ◽  
Tutoring Systems ◽  
User Input ◽  
Controlled Natural Language

A continuing problem for ANLP (compared with NLP) is that language tends to be more natural in ANLP than that examined in more controlled natural language processing (NLP) studies. Specifically, ineffective or misleading feedback can result from faulty assessment of misspelled words. This chapter describes the Harmonizer system for addressing the problem of user input irregularities (e.g., typos). The Harmonizer is specifically designed for Intelligence Tutoring Systems (ITSs) that use NLP to provide assessment and feedback based on the typed input of the user. Our approach is to “harmonize” similar words to the same form in the benchmark, rather than correcting them to dictionary entries. This chapter describes the Harmonizer, and evaluates its performance using various computational approaches on unedited input from high school students in the context of an ITS (i.e., iSTART). Our results indicate that various metric approaches to NLP (such as word-overlap cohesion scores) are moderately affected when student errors are filtered by the Harmonizer. Given the prevalence of typing errors in the sample, the study substantiates the need to “clean” typed input in comparable NLP-based learning systems. The Harmonizer provides such ability and is easy to implement with light processing requirements.

scholarly journals Lessons Learned from Teaching Machine Learning and Natural Language Processing to High School Students

2020 ◽  
Vol 34 (09) ◽  
pp. 13397-13403
Author(s):  
Narges Norouzi ◽  
Snigdha Chaturvedi ◽  
Matthew Rutledge
Keyword(s):  
Machine Learning ◽  
High School ◽  
High School Students ◽  
Natural Language Processing ◽  
Natural Language ◽  
Language Processing ◽  
Teaching Machine ◽  
Lessons Learned ◽  
School Students ◽  
Gender Discrepancies

This paper describes an experience in teaching Machine Learning (ML) and Natural Language Processing (NLP) to a group of high school students over an intense one-month period. In this work, we provide an outline of an AI course curriculum we designed for high school students and then evaluate its effectiveness by analyzing student's feedback and student outcomes. After closely observing students, evaluating their responses to our surveys, and analyzing their contribution to the course project, we identified some possible impediments in teaching AI to high school students and propose some measures to avoid them. These measures include employing a combination of objectivist and constructivist pedagogies, reviewing/introducing basic programming concepts at the beginning of the course, and addressing gender discrepancies throughout the course.

How Much Knowledge Is Too Little? When a Lack of Knowledge Becomes a Barrier to Comprehension

2019 ◽  
Vol 30 (9) ◽  
pp. 1344-1351 ◽  
Author(s):  
Tenaha O’Reilly ◽  
Zuowei Wang ◽  
John Sabatini
Keyword(s):  
High School ◽  
High School Students ◽  
Natural Language Processing ◽  
Language Processing ◽  
Positive Relation ◽  
Specific Topic ◽  
School Students ◽  
Knowledge Test ◽  
Processing Techniques ◽  
The Relationship

Have you ever found it difficult to read something because you lack knowledge on the topic? We investigated this phenomenon with a sample of 3,534 high school students who took a background-knowledge test before working on a reading-comprehension test on the topic of ecology. Broken-line regression revealed a knowledge threshold: Below the threshold, the relationship between comprehension and knowledge was weak (β = 0.18), but above the threshold, a strong and positive relation emerged (β = 0.81). Further analyses indicated that certain topically relevant words (e.g., ecosystem, habitat) were more important to know than others when predicting the threshold, and these keywords could be identified using natural-language-processing techniques. Collectively, these results may help identify who is likely to have a problem comprehending information on a specific topic and, to some extent, what knowledge is likely required to comprehend information on that topic.

scholarly journals Plan-Do-Review-Share-Happy (Plandoresh) strategy as an effort of developing vocational high school students’ independent learning

2021 ◽  
Vol 11 (1) ◽  
Author(s):  
Aftoni Aftoni ◽  
I Wayan Susila ◽  
Any Sutiadiningsih ◽  
Muhammad Kris Yuan Hidayatulloh
Keyword(s):  
High School ◽  
High School Students ◽  
Learning Systems ◽  
Independent Learning ◽  
Vocational School ◽  
Vocational High School ◽  
School Students ◽  
Routine Tasks ◽  
Level Of Thinking ◽  
Descriptive Method

When computers take over routine tasks at work, a number of employees engage in tasks that require independent problem solving . Current learning systems should encourage students to move beyond the level of thinking that is lower in order to become personally self-sufficient . The purpose of this study was to test the validity of the Plan-Do-Review-Share-Happy (Plandoresh) strategy stages as an effort to develop independent learning for vocational school students. This study used a descriptive method with the aim of obtaining the validity of the Plandoresh strategy stages with a random sample of 78 respondents. The results showed that: 1) the Plan stage is valid with r count > r table of 0.849 > 0.227, 2) the Do stage is valid with r count > r table of 0.873, 3) the Review stage is valid with r count > r tabel 0,856, 4) Tahap Share valid dengan r hitung> r tabel 0,868, 5) Tahap Happy valid dengan r hitung > r tabel 0,929. Hasil ini menunjukkan bahwa tahapan strategi Plandores berlaku untuk diterapkan dalam upaya untuk mengembangkan belajar mandiri untuk kejuruan sekolah siswa.

Articulatory Intervention for the Visually Impaired

1979 ◽  
Vol 10 (3) ◽  
pp. 139-144
Author(s):  
Cheri L. Florance ◽  
Judith O’Keefe
Keyword(s):  
High School ◽  
High School Students ◽  
Behavior Change ◽  
Visually Impaired ◽  
School Students ◽  
Handicapped Children ◽  
Paired Stimuli ◽  
Visually Handicapped ◽  
Parent Program

A modification of the Paired-Stimuli Parent Program (Florance, 1977) was adapted for the treatment of articulatory errors of visually handicapped children. Blind high school students served as clinical aides. A discussion of treatment methodology, and the results of administrating the program to 32 children, including a two-year follow-up evaluation to measure permanence of behavior change, is presented.

A Triarchic Analysis of an Aptitude-Treatment Interaction

1999 ◽  
Vol 15 (1) ◽  
pp. 3-13 ◽  
Author(s):  
Robert J. Sternberg ◽  
Elena L. Grigorenko ◽  
Michel Ferrari ◽  
Pamela Clinkenbeard
Keyword(s):  
High School ◽  
High School Students ◽  
Introductory Psychology ◽  
College Level ◽  
School Students ◽  
Treatment Interaction ◽  
Aptitude Treatment Interaction ◽  
Psychology Course

Summary: This article describes a triarchic analysis of an aptitude-treatment interaction in a college-level introductory-psychology course given to selected high-school students. Of the 326 total participants, 199 were selected to be high in analytical, creative, or practical abilities, or in all three abilities, or in none of the three abilities. The selected students were placed in a course that either well matched or did not match their pattern of analytical, creative, and practical abilities. All students were assessed for memory, analytical, creative, and practical achievement. The data showed an aptitude-treatment interaction between students' varied ability patterns and the match or mismatch of these abilities to the different instructional groups.

Identity Exploration and Commitment of Albanian Youth as a Function of Social Opportunity Structure

2006 ◽  
Vol 11 (4) ◽  
pp. 268-276 ◽  
Author(s):  
Aida Orgocka ◽  
Jasna Jovanovic
Keyword(s):  
High School ◽  
High School Students ◽  
Identity Development ◽  
Youth Development ◽  
Female Students ◽  
Male Students ◽  
Opportunity Structure ◽  
School Students ◽  
Identity Exploration

This study examined how social opportunity structure influences identity exploration and commitment of Albanian high school students. A total of 258 students completed a questionnaire that gauged their identity exploration and commitment in three domains: education, occupation, and family. ANOVA results indicated that, overall, students scored highest in exploration in the domain of education and in commitment in the domain of family. Students' exploration and commitment were linked to gender. Albanian female students scored higher than male students in exploration and commitment regarding education and family. Perceived work opportunities in Albania or abroad also significantly moderated participants' exploration in the domain of education and were associated with commitment in education and occupation. As one of the first studies to explore Albanian youth's identity development in relation to social opportunity structure, findings are discussed in light of furthering the field of Albanian adolescent and youth development.

Mobilizing for Some

2016 ◽  
Vol 28 (3) ◽  
pp. 123-135 ◽  
Author(s):  
Raffael Heiss ◽  
Jörg Matthes
Keyword(s):  
High School ◽  
Social Media ◽  
High School Students ◽  
Experimental Design ◽  
Collective Efficacy ◽  
Political Efficacy ◽  
Negative Effects ◽  
School Students ◽  
Positive Effects ◽  
Specific Factors

Abstract. This study investigated the effects of politicians’ nonparticipatory and participatory Facebook posts on young people’s political efficacy – a key determinant of political participation. We employed an experimental design, using a sample of N = 125 high school students (15–20 years). Participants either saw a Facebook profile with no posts (control condition), nonparticipatory posts, or participatory posts. While nonparticipatory posts did not affect participants’ political efficacy, participatory posts exerted distinct effects. For those high in trait evaluations of the politician presented in the stimulus material or low in political cynicism, we found significant positive effects on external and collective efficacy. By contrast, for those low in trait evaluations or high in cynicism, we found significant negative effects on external and collective efficacy. We did not find any effects on internal efficacy. The importance of content-specific factors and individual predispositions in assessing the influence of social media use on participation is discussed.

Sign in / Sign up

Export Citation Format

Share Document