Quizbot: Exploring Formative Feedback with Conversational Interfaces

Abstract

Conversational interfaces also called chatbots recently disrupted the Internet and opened up endless opportunities for assessment and learning. Formative feedback providing learners with a practical instruction for improvement is one of the challenging tasks in, for instance self-assessment settings and self-directed learning. This becomes even more challenging if user's personal information such as learning history and previous achievements cannot be exploited for data protection reasons or are simply not available. This study seeks to explore the opportunities of providing formative feedback in chatbot-based assessment. Two main challenges were faced: the limitations of the messenger as an interface that restricts visual representation of the quiz questions, and zero information about the user to generate adaptive feedback. Two types of feedback were investigated regarding their formative effect: immediate feedback, which was given after answering a question, and cumulative feedback detailing strengths and weaknesses of the user in each of the topics covered along with the directives for improvement. A chatbot called SQL Quizbot was deployed on Facebook Messenger for the purposes of this study 1. A survey conducted to disclose users' perception of the feedback reveals that more than 80% of the users find immediate feedback helpful. Overall this study shows that chatbots have a great potential as an aiding tool for e-learning systems to include an interactive component into feedback in order to increase user motivation and retention.

The Dawn of the Human-Machine Era: A forecast of new and emerging language technologies

“…Nevertheless, making tutoring chatbots more "human-like" while assigning a new role to them (not similar to a teacher) may help to resolve authority problems. Two examples of such roles have been explored in and Vijayakumar et al (2018). The former explores using chatbots that simulate native speaker peers for practicing L2 conversation (equal-power relationship).…”

Personalisation methods in e‐learning‐A literature review

“…Different approaches exist and have been used in the literature for providing adaptive feedback. Most common is providing generic textual feedback based on the performance and cognitive level of the student [275], while the limited number of studies incorporate more specific approaches such are: video recordings with expert feedback [74,90], envisioning grammar mistakes during sentence construction [116] and incorporation of learning agents [288]. According to Bimba et al [48] adaptive feedback is generated based on the four adaptation characteristics: means (Which information about the learner is used for adaptation?…”

The Design of an Intelligent Chatbot with Natural Language Processing Capabilities to Support Learners

“…The functionalities of the chatbot have extended to beyond engaging in dialogues with humans [10]. Many of todays' e-commerce chatbots are programmed to infer the user's intent from just a few words using natural language processing (NLP) [2].…”

“…Traditionally, the chatbot must have excellent conversational abilities to be qualified as useful [10]. The modern day chatbot has some features that make it suitable for engaging students in higher education.…”

“…Thirdly, students can use commands and keywords to freely navigate to quiz themselves on different topics. Fourthly, the chatbot can give response in multimedia format such as images and voice [10]. In Figure 2, the smiley icon with sunglasses is shown when the student answered the question correctly.…”