Perusall: University learning-teaching innovation employing social annotation and machine learning

IF 0.4 Q4 COMPUTER SCIENCE, INTERDISCIPLINARY APPLICATIONS

Qwerty Pub Date : 2020-12-23 DOI:10.30557/QW000030

G. Cecchinato, L. Foschi

{"title":"Perusall: University learning-teaching innovation employing social annotation and machine learning","authors":"G. Cecchinato, L. Foschi","doi":"10.30557/QW000030","DOIUrl":null,"url":null,"abstract":"This paper presents the learning-teaching innovation process of a \nUniversity course. The traditional elements of the teaching-learning \nprocess (lecture, study, exam) involving students in ongoing activities \nhave changed. The paper focuses on the learning changes introduced \nby social annotation activities carried out through the Perusall web \nenvironment. In particular, Perusall functionalities that assess students’ participation were examined. These rely on multiple indicators set by the teacher, and a Machine Learning algorithm, which assesses the quality of annotations. A study was carried out to examine the validity of this process by analysing the relationship between Perusall algorithm’s scores and teacher’s scores, and how students perceive the automated scoring. The relationship was investigated through the Spearman correlation coefficient and Kendall’s coefficient of concordance. \nThematic analysis was used to analyse the qualitative data \nconcerning students’ perceptions. The results indicate that the Perusall algorithm provided scores quite similar to those of the teacher, and \nthat students positively perceived the automated scoring.","PeriodicalId":41384,"journal":{"name":"Qwerty","volume":"107 1","pages":"45-67"},"PeriodicalIF":0.4000,"publicationDate":"2020-12-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"6","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"Qwerty","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.30557/QW000030","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q4","JCRName":"COMPUTER SCIENCE, INTERDISCIPLINARY APPLICATIONS","Score":null,"Total":0}

引用次数: 6

Abstract

This paper presents the learning-teaching innovation process of a University course. The traditional elements of the teaching-learning process (lecture, study, exam) involving students in ongoing activities have changed. The paper focuses on the learning changes introduced by social annotation activities carried out through the Perusall web environment. In particular, Perusall functionalities that assess students’ participation were examined. These rely on multiple indicators set by the teacher, and a Machine Learning algorithm, which assesses the quality of annotations. A study was carried out to examine the validity of this process by analysing the relationship between Perusall algorithm’s scores and teacher’s scores, and how students perceive the automated scoring. The relationship was investigated through the Spearman correlation coefficient and Kendall’s coefficient of concordance. Thematic analysis was used to analyse the qualitative data concerning students’ perceptions. The results indicate that the Perusall algorithm provided scores quite similar to those of the teacher, and that students positively perceived the automated scoring.

查看原文本刊更多论文

Perusall:运用社会注释和机器学习的大学学与教创新

本文介绍了大学课程学与教的创新过程。让学生参与持续活动的教学过程的传统要素(讲座、学习、考试)发生了变化。本文主要研究通过Perusall web环境开展社会标注活动所带来的学习变化。特别是，Perusall功能评估学生的参与进行了检查。这些依赖于教师设置的多个指标，以及评估注释质量的机器学习算法。通过分析Perusall算法得分与教师得分之间的关系，以及学生如何看待自动评分，进行了一项研究，以检验这一过程的有效性。通过Spearman相关系数和Kendall协调系数对二者的关系进行了研究。主题分析法用于分析学生认知的定性数据。结果表明，Perusall算法提供的分数与老师的分数非常相似，学生对自动评分有积极的看法。

本文章由计算机程序翻译，如有差异，请以英文原文为准。

求助全文

约1分钟内获得全文求助全文

来源期刊

Qwerty COMPUTER SCIENCE, INTERDISCIPLINARY APPLICATIONS-

CiteScore

2.40

自引率

15.40%

发文量

期刊介绍： Qwerty is the commonly accepted name for the computer keyboard, comprising the first six letters of its top row. When typewriters were first introduced, the keys were arranged in alphabetical order. However this order meant that people typed too quickly such that the keys soon became entangled. To counter this, the keys were displayed in random order and typing speeds accordingly slowed down. In later years, despite the fact that the problem of speed had been completely overcome, the keyboard retained its random order. In our view, this represents an excellent metaphor for the entanglement of culture and technological tools. In actual fact, we regard computer-based technologies as cultural artefacts, representing different depths in the daily work and study activity of individuals, social groups, and institutions. We believe that different models of computer use and activity within online environments mediate social interaction. As such, the relationship between culture and technological tools is becoming more and more complex and now provides an opportunity for determining new models of cognitive, psychological, and social interaction. Qwerty hopes to be a place where such issues can be discussed and developed. The journal arises from a growing awareness of the need to develop research and reflection on the impact, effects and nature of technology use and, as such, is intended to be a genuinely cross-disciplinary forum. Qwerty wishes to provide a forum for discussion on the use of new technologies aimed at anyone interested in the use of technology in such fields as education, training, social and university research, including the cultural, social, pedagogical, psychological, economic, professional, ethical and aesthetical aspects of technology use.