Abstract: In higher education, low teacher-student ratios can make it difficult for studen ...
Expand
Abstract: In higher education, low teacher-student ratios can make it difficult for students to receive immediate and interactive help. Chatbots, increasingly used in various scenarios such as customer service, work productivity, and healthcare, might be one way of helping instructors better meet student needs. However, few empirical studies in the field of Information Systems (IS) have investigated pedagogical chatbot efficacy in higher education and fewer still discuss their potential challenges and drawbacks. In this research we address this gap in the IS literature by exploring the opportunities, challenges, efficacy, and ethical concerns of using chatbots as pedagogical tools in business education. In this two study project, we conducted a chatbot-guided interview with 215 undergraduate students to understand student attitudes regarding the potential benefits and challenges of using chatbots as intelligent student assistants. Our findings revealed the potential for chatbots to help students learn basic content in a responsive, interactive, and confidential way. Findings also provided insights into student learning needs which we then used to design and develop a new, experimental chatbot assistant to teach basic AI concepts to 195 students. Results of this second study suggest chatbots can be engaging and responsive conversational learning tools for teaching basic concepts and for providing educational resources. Herein, we provide the results of both studies and discuss possible promising opportunities and ethical implications of using chatbots to support inclusive learning.
Collapse
Semantic filters:
no code development platform
Topics:
artificial intelligence IT career anonymity user experience accounting
Methods:
chatbot survey qualitative interview personal interview machine learning
A Conversational Goal Setting Buddy for Student Learning
2022 | Americas Conference on Information Systems | Citations: 8
Abstract: Time management and goal setting skills are essential for student academic succ ...
Expand
Abstract: Time management and goal setting skills are essential for student academic success in higher education. Meanwhile, the recent advances of chatbots offer new opportunities to support goal setting in a conversational way. In this preliminary research, we investigate the effects of chatbots as a conversational goal setting tool for student learning. We developed a chatbot called Sammy that invites students to pledge their study goals and reflect on their goal completion. We conducted a 7-day study among 70 undergraduate students. Analysis on pre-and post-study surveys indicated a significant improvement in student perceived time management in learning goals. Analysis on student daily check-in with Sammy showed an upward trend of student satisfaction in goal completion and confidence in future goal setting. In the future, we will conduct a more comprehensive mixed-method analysis, improve the functionalities and usability of Sammy, and conduct longitudinal studies.
Collapse
Semantic filters:
no code development platform
Topics:
no code development platform
Methods:
chatbot survey parametric test experiment Student's t-test
Off-the-Shelf Technologies for Sentiment Analysis of Social Media Data: Two Empirical Studies
2020 | Americas Conference on Information Systems | Citations: 0
Authors: Carvalho, Arthur; Harris, Lucas
Abstract: Off-the-shelf technologies provided by major cloud platforms promise to facilit ...
Expand
Abstract: Off-the-shelf technologies provided by major cloud platforms promise to facilitate and democratize the use of artificial intelligence techniques. Organizations can now apply highly sophisticated, pre-trained models in a variety of situations, such as when analyzing the sentiment behind social media posts. Among other uses, this enables organizations to better understand their consumers' opinions regarding products and/or services. In this paper, we first review technologies for sentiment analysis provided by major cloud platforms. We then compare the accuracy of these technologies against a technique widely used in managerial and information systems studies, namely the bag-of-words approach. Our two empirical studies use social media data collected from Twitter (short posts) and Facebook (long posts). We find that all the studied off-the-shelf technologies for sentiment analysis are vastly more accurate than the bag-of-words approach. We conclude the paper by discussing our results in light of the recent rise of low/no-code development practices. KeywordsSentiment analysis, artificial intelligence, social media analytics, software as a service. IntroductionRecent years have seen tremendous growth in interest in artificial intelligence (AI), with application domains ranging from playful settings, such as soccer robot (Oliveira et al., 2009;Carvalho and Oliveira, 2011) and artificial poker players (Brown and Sandholm, 2018), to energy trading (Babic et al., 2017) and life-saving scenarios, such as rescue robots (Davids, 2002) and the prediction of heart transplant outcomes (Dag et al., 2016). Although not consensual, AI can be defined as "the study of agents that receive percepts from the environment and perform actions" (Russell and Norvig, 2016). Agents can be from very basic scripts written in any computational language to fully autonomous robots. This agent-centric perspective brings together several research areas under a common framework. For example, machine learning is about how agents can learn in/from an environment, knowledge representation is about how agents represent their knowledge, and natural language processing (NLP) is about how agents can communicate and understand each other and human beings. It is this latter area that we focus on in this paper.One of the primary focuses of NLP is to acquire information from written language (Russell and Norvig, 2016). This is a challenging task given the nature of the underlying data, i.e., textual data might be ambiguous, contain typos, grammar mistakes, jargon, slangs, etc. Using computational, statistical, and linguistic techniques, there are many types of textual analysis one can perform, e.g., text categorization, text clustering, automatic summarization, topic modeling, and sentiment analysis. We concentrate on sentiment analysis, with a particular focus on the analysis of social media data.Sentiment analysis aims at understanding and quantifying the sentiment behind a text (Liu, 2012), e.g., it is used when one wants to determine whether a certain piece of text is positive, negative, or neutral. This,
Collapse
Semantic filters:
no code development platform
Topics:
Twitter social media cloud computing artificial intelligence Facebook
Methods:
sentiment analysis natural language processing experiment machine learning Z-test
