scholarly journals Explanation Strategies as an Empirical-Analytical Lens for Socio-Technical Contextualization of Machine Learning Interpretability

2022 ◽  
Vol 6 (GROUP) ◽  
pp. 1-25
Author(s):  
Jesse Josua Benjamin ◽  
Christoph Kinkeldey ◽  
Claudia Müller-Birn ◽  
Tim Korjakow ◽  
Eva-Maria Herbst
Keyword(s):  
Machine Learning ◽  
Participatory Design ◽  
Design Research ◽  
Philosophy Of Technology ◽  
Collaborative Work ◽  
Empirical Studies ◽  
Sense Making ◽  
Proof Of Concept ◽  
Visualization System ◽  
Computer Supported Collaborative Work

During a research project in which we developed a machine learning (ML) driven visualization system for non-ML experts, we reflected on interpretability research in ML, computer-supported collaborative work and human-computer interaction. We found that while there are manifold technical approaches, these often focus on ML experts and are evaluated in decontextualized empirical studies. We hypothesized that participatory design research may support the understanding of stakeholders' situated sense-making in our project, yet, found guidance regarding ML interpretability inexhaustive. Building on philosophy of technology, we formulated explanation strategies as an empirical-analytical lens explicating how technical explanations mediate the contextual preferences concerning people's interpretations. In this paper, we contribute a report of our proof-of-concept use of explanation strategies to analyze a co-design workshop with non-ML experts, methodological implications for participatory design research, design implications for explanations for non-ML experts and suggest further investigation of technological mediation theories in the ML interpretability space.

Designing a creative programming unit within the elementary school core curriculum

2020 ◽  
Author(s):  
Yumiko Murai ◽  
Ryohei Ikejiri ◽  
Yuhei Yamauchi ◽  
Ai Tanaka ◽  
Seiko Nakano
Keyword(s):  
Core Curriculum ◽  
Design Research ◽  
Empirical Studies ◽  
School Curriculum ◽  
Educational Design ◽  
Current Trends ◽  
Educational Design Research ◽  
Creative Learning ◽  
Uncertain Future ◽  
The Impact

Cultivating children’s creativity and imagination is fundamental to preparing them for an increasingly complex and uncertain future. Engaging in creative learning enables children to think independently and critically, work cooperatively, and take risks while actively engaging in problem solving. While current trends in education, such as maker movements and computer science education, are dramatically expanding children’s opportunities for engagement in creative learning, comparatively few empirical studies explore how creative learning can be integrated into the school curriculum. The educational design research described in this paper focuses on a curriculum unit that enables students to engage with creative learning through computer programming activities while meeting curriculum goals. The data provided in this paper were drawn from three classroom tryouts, the results of which were used to drive an iterative design process. This paper also shares several insights on the impact of creative learning in curriculum teaching.

A Review on Machine-Learning Based Code Smell Detection Techniquesin Object-Oriented Software System(s)

2020 ◽  
Vol 13 ◽  
Author(s):  
Amandeep Kaur ◽  
Sushma Jain ◽  
Shivani Goel ◽  
Gaurav Dhiman
Keyword(s):  
Machine Learning ◽  
Programming Languages ◽  
Software Quality ◽  
Empirical Studies ◽  
Statistical Testing ◽  
Machine Learning Techniques ◽  
Support Vector ◽  
Code Smells ◽  
Detection Techniques ◽  
Code Smell

Context: Code smells are symptoms, that something may be wrong in software systems that can cause complications in maintaining software quality. In literature, there exists many code smells and their identification is far from trivial. Thus, several techniques have also been proposed to automate code smell detection in order to improve software quality. Objective: This paper presents an up-to-date review of simple and hybrid machine learning based code smell detection techniques and tools. Methods: We collected all the relevant research published in this field till 2020. We extracted the data from those articles and classified them into two major categories. In addition, we compared the selected studies based on several aspects like, code smells, machine learning techniques, datasets, programming languages used by datasets, dataset size, evaluation approach, and statistical testing. Results: Majority of empirical studies have proposed machine- learning based code smell detection tools. Support vector machine and decision tree algorithms are frequently used by the researchers. Along with this, a major proportion of research is conducted on Open Source Softwares (OSS) such as, Xerces, Gantt Project and ArgoUml. Furthermore, researchers paid more attention towards Feature Envy and Long Method code smells. Conclusion: We identified several areas of open research like, need of code smell detection techniques using hybrid approaches, need of validation employing industrial datasets, etc.

Microplastic adulteration in homogenized fish and seafood - a mid-infrared and machine learning proof of concept

2021 ◽  
pp. 119985
Author(s):  
Stephanie Owen ◽  
Samuel Cureton ◽  
Mathew Szuhan ◽  
Joel McCarten ◽  
Panagiota Arvanitis ◽  
...  
Keyword(s):  
Machine Learning ◽  
Proof Of Concept ◽  
Mid Infrared

Translanguaging design in a third grade Chinese Language Arts class

2021 ◽  
Vol 0 (0) ◽  
Author(s):  
Zhongfeng Tian
Keyword(s):  
Language Arts ◽  
Bilingual Education ◽  
Participatory Design ◽  
Dual Language ◽  
Design Research ◽  
Chinese Language ◽  
Bilingual Learners ◽  
Allocation Policy ◽  
Link Type ◽  
Dual Language Bilingual Education

Abstract Traditionally strict language separation policies in dual language bilingual education (DLBE) programs reflect parallel monolingualism and have been criticized as failing to recognize the sociolinguistic realities of bilingual students (García, Ofelia & Angel M. Y. Lin. 2017. Translanguaging in bilingual education. In Ofelia García, Angel M. Y. Lin & Stephen May (eds.), Bilingual and multilingual education, 117–130. Cham: Springer International Publishing). To recognize the dynamic nature of bilingualism and leverage bilingual learners’ full semiotic and linguistic repertoire as a resource, this study looks at how to strategically and purposefully develop flexible and multilingual educational spaces in a third grade Chinese Language Arts (CLA) class in a Mandarin-English DLBE program in the New England area, U.S. Drawing upon Sánchez, María Teresa (Maite), Ofelia García & Cristian Solorza. 2018. Reframing language allocation policy in dual language bilingual education. Bilingual Research Journal 41(1). 37–51. https://doi.org/10.1080/15235882.2017.1405098, translanguaging allocation policy framework, the researcher and the teacher co-designed and implemented translanguaging documentation, translanguaging rings, and translanguaging transformation spaces in the CLA class throughout the school year of 2018–19. Taking the form of participatory design research (Bang, Megan & Shirin Vossoughi. 2016. Participatory design research and educational justice: Studying learning and relations within social change making. Cognition and Instruction 34(3). 173–193. https://doi.org/10.1080/07370008.2016.1181879), this collaborative inquiry demonstrates that translanguaging pedagogies could promote student engagement, contribute to their academic learning, and build home-school connections. It aims to provide authentic, sustainable knowledge for both researchers and practitioners to better serve bilingual learners in DLBE programs.

scholarly journals Using Participatory Design to Design an eHealth Well-Being Program

2021 ◽  
Vol 18 (14) ◽  
pp. 7250
Author(s):  
Yannick van Hierden ◽  
Timo Dietrich ◽  
Sharyn Rundle-Thiele
Keyword(s):  
Best Practices ◽  
Health Professionals ◽  
Participatory Design ◽  
Online Community ◽  
Well Being ◽  
Proof Of Concept ◽  
End User ◽  
Ehealth Intervention ◽  
Pilot Intervention ◽  
User Friendly

In recent years, the relevance of eHealth interventions has become increasingly evident. However, a sequential procedural application to cocreating eHealth interventions is currently lacking. This paper demonstrates the implementation of a participatory design (PD) process to inform the design of an eHealth intervention aiming to enhance well-being. PD sessions were conducted with 57 people across four sessions. Within PD sessions participants experienced prototype activities, provided feedback and designed program interventions. A 5-week eHealth well-being intervention focusing on lifestyle, habits, physical activity, and meditation was proposed. The program is suggested to be delivered through online workshops and online community interaction. A five-step PD process emerged; namely, (1) collecting best practices, (2) participatory discovery, (3) initial proof-of-concept, (4) participatory prototyping, and (5) pilot intervention proof-of-concept finalisation. Health professionals, behaviour change practitioners and program planners can adopt this process to ensure end-user cocreation using the five-step process. The five-step PD process may help to create user-friendly programs.

Cognitive, Affective, and Politicized Trust in a Community Youth Program: A Participatory Design Research Project

2021 ◽  
Author(s):  
Cinamon Sunrise Bailey ◽  
Ibrahim Oluwajoba Adisa ◽  
Hazel Vega ◽  
Golnaz Arastoopour Irgens
Keyword(s):  
Participatory Design ◽  
Design Research ◽  
Research Project ◽  
Youth Program

Design Research Strategies for a Total Artificial Heart

2017 ◽  
Vol 61 (1) ◽  
pp. 593-596
Author(s):  
L. Bryant Foster
Keyword(s):  
Participatory Design ◽  
Artificial Heart ◽  
Design Research ◽  
Total Artificial Heart ◽  
Research Strategies ◽  
Regulatory Requirements ◽  
Regulatory Constraints ◽  
Regulatory Submission ◽  
Conducting Research ◽  
Validation Testing

Human factors formative and validation testing have become a part of the regulatory submission process for new medical devices in the U.S. and Europe. However, there are additional design research methods that manufacturers should consider implementing before and during development to ensure their products are safe, usable and desirable. Many manufacturers avoid conducting design research due to regulatory requirements to document adverse events. This paper discusses contextual research and participatory design performed to gather user needs for a new Total Artificial Heart TAH-t) user interface as well as strategies for conducting research with current users to comply with regulatory constraints.

Sign in / Sign up

Export Citation Format

Share Document