FAQ chatbot and inclusive learning in massive open online courses

Han, Songhee; Lee, Min Kyung

doi:10.1016/j.compedu.2021.104395

Cited by 53 publications

(38 citation statements)

References 24 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…AI‐based conversational agents have attracted extensive attention in educational communities to provide automatic support for teaching and learning. Current educational studies on CAs mainly focused on their capability to generate responses of quality or users' experience with them (eg, Li & Xing, 2021; Han & Lee, 2021; Pereira et al, 2019). Another critical issue of CAs that lacks investigation in education is how to enhance their safety.…”

Section: Discussionmentioning

confidence: 99%

“…Their results showed that most students (90%) reported having higher engagement to study with the chatbot‐companion. In the study of Han and Lee (2021), the researchers built an English‐based CA to answer students' frequently asked questions in a MOOC. The researchers showed that the effectiveness of the CA could be associated with various factors.…”

Section: Introductionmentioning

confidence: 99%

“…CA and chatbot are two terms often used interchangeably (Syvänen & Valentini, 2020), which are defined as human‐developed software powered by natural language processing techniques (NLP) to spontaneously respond to human languages (Wang et al, 2021). Most studies on AI‐based CA in education have focused on responses' quality, engagingness, and learner experience (eg, Han & Lee, 2021; Li & Xing, 2021; Pereira et al, 2019). For example, Li and Xing (2021) built an AI‐based CA to socio‐emotionally support students in a massive open online course (MOOC).…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Building socially responsible conversational agents using big data to support online learning: A case with Algebra Nation

Xing

Leite

2022

Brit J Educational Tech

View full text Add to dashboard Cite

A discussion forum is a valuable tool to support student learning in online contexts. However, interactions in online discussion forums are sparse, leading to other issues such as low engagement and dropping out. Recent educational studies have examined the affordances of conversational agents (CA) powered by artificial intelligence (AI) to automatically support student participation in discussion forums. However, few studies have paid attention to the safety of CAs. This study aimed to address the safety challenges of CAs constructed with educational big data to support learning. Specifically, we proposed a safety‐aware CA model, benchmarked with two state‐of‐the‐art (SOTA) models, to support high school student learning in an online algebra learning platform. We applied automatic text analysis to evaluate the safety and socio‐emotional support levels of CA‐generated and human‐generated texts. A large dataset was used to train and evaluate the CA models, which consisted of all discussion post‐reply pairs (n = 2,097,139) by 71,918 online math learners from 2015 to 2021. Results show that while SOTA models can generate supportive texts, their safety is compromised. Meanwhile, our proposed model can effectively enhance the safety of generated texts while providing comparable support. What is already known about this topic Online discussion forums have been plagued by a lack of interaction among students due to factors such as expectations to receive no response and perceptions of topic irrelevance which lead to low motivation to participate. AI‐based conversational agents can automatically support students' interactions in online discussion forums at a large scale, and their generated responses can be human‐like, contextually coherent and socio‐emotionally supportive. Unsafe discourse exchanges between students and conversational agents can be dangerous as identity attacks, aggravation and bullying behaviours embedded in discourses can disrupt students' knowledge inquiry and negatively influence student motivation and engagement. However, few educational studies have paid attention to the safety of conversational agents. What this paper adds This study proposes and synthesized strategies to build AI‐based conversational agents that automatically support online discussions with safe and supportive discourses. This study reveals the relationship between discourse safety and social support, suggesting supportive discourses can also be unsafe. This study enriches the literature on educational conversational agents by synthesizing a conceptual framework on discourse safety and social support, and by proposing concrete algorithmic strategies to improve the safety of conversational agents. Implications for practice and/or policy Researchers and practitioners can adopt strategies in this study such as generation control, open‐sourced models and public API services to evaluate students' discourse safety for early intervention or modify existing conversational agents to be safety‐aware. Practitioners can utilize...

show abstract

Section: Discussionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Building socially responsible conversational agents using big data to support online learning: A case with Algebra Nation

Xing

Leite

2022

Brit J Educational Tech

View full text Add to dashboard Cite

show abstract

“…Também, nota-se uma preocupac ¸ão dos estudos secundários em tentar esclarecer como os chatbots são construídos e usados na educac ¸ão. Dois estudos secundários acabaram retratando como os chatbots são explorados em contextos de uso específicos.Apesar disso, não existem esforc ¸os para compreender o uso do chatbot na educac ¸ão a distância, um dos tópicos que tem ganhado espac ¸o em fóruns de discussão da área [Han and Lee 2022].Nos resultados deste estudo, algumas oportunidades de pesquisa foram propostas. Elas podem ser acolhidas pela comunidade para direcionar as pesquisas existentes.…”

Section: Conclusõesunclassified

O que revelam os estudos secundários sobre chatbots na educação?

Paschoal

Conte

Souza

2022

Anais Do XXXIII Simpósio Brasileiro De Informática Na Educação (SBIE 2022)

View full text Add to dashboard Cite

Chatbots têm sido estabelecidos com múltiplos propósitos para apoiar atividades educacionais. Em razão disso, o número de relatos sobre o impacto decorrente do uso desse tipo de software tem aumentado e estudos secundários têm surgido na literatura. Apesar de existirem estudos secundários, ainda não há estudos terciários que ofereçam uma visão crítica sobre a literatura disponível, especialmente não há um entendimento concreto sobre as evidências já obtidas e o que ainda é preciso ser desenvolvido pela comunidade. Este artigo busca amenizar essa lacuna, categorizando os estudos secundários relacionados a chatbots educacionais e oferecendo uma análise crítica sobre os estudos realizados. Um inventario de mapeamentos e revisões sistemáticas é fornecido para pesquisadores e profissionais que possuem interesse na temática.

show abstract

“…According to the respondents ' answers, half of the survey participants did not answer the question, which means that they do not see their role and participation in the development of their practice in this regard, or they will do everything in the best way. However, we cannot accept this last opinion, because the results of the majority survey are a clear example of their incompetence in the field of inclusive education (Han & Lee, 2022;Conceição & Heitor, 2002;Gregg et al, 2012). Some respondents mainly note the increase of knowledge in the field of inclusive education and consider it important to have specialists in the garden.…”

Section: Introductionmentioning

confidence: 99%

importance of inclusive learning and teaching enviroment and teacher reflection

Dzamukashvili

2022

ijhla

View full text Add to dashboard Cite

The research aims to identify the knowledge, attitudes, and practices of the preschool teachers of the target group regarding the implementation/development of inclusive education. Structure/methodology /approach-10 teachers participated in this study, who were also involved in the research carried out within the framework of the project "teacher reflection for quality early inclusive education". An early inclusive education environment self-reflection method was used, developed within the framework of the early childhood inclusive education (I) project implemented by the European agency for special needs and inclusive education from 2015 to 2017 (www.european-agency.org/agency-projects/inclusive-early childhood-education), our adapted version. Research is qualitative. The reflection method included four open questions: This article reflects educators on the "inclusive environment of teaching and learning". Conclusion: the survey participants ' responses prove that educators and educators are aware of the desire and need to increase their knowledge about the inclusive environment of learning and teaching, but they find it difficult to reflect on these issues and analyze them based on their practice, which can again be considered as their low competence in this regards. Novelty/value: the study of teacher-educator reflection is not conducted on the example of our practice.

show abstract

FAQ chatbot and inclusive learning in massive open online courses

Cited by 53 publications

References 24 publications

Building socially responsible conversational agents using big data to support online learning: A case with Algebra Nation

Building socially responsible conversational agents using big data to support online learning: A case with Algebra Nation

O que revelam os estudos secundários sobre chatbots na educação?

importance of inclusive learning and teaching enviroment and teacher reflection

Contact Info

Product

Resources

About