A Natural Language Conversational System for Online Academic Advising

We have designed an academic advising online system to advise college students using natural language conversations. The system embeds knowledge of current and future teaching schedules, degree requirements, course prerequisites and various administrative procedures. While this information can be found by searching several university websites and catalogs, students continually ask human advisors these questions during their limited face-toface time, which limits deeper developmental and educative advising that is only available from human advisors. Our system enhances the advising experience by offering a source for instant academic advice that does not require student training or additional human resources. The system contains a pattern-matching dialog management system with access via a web browser. We describe the motivation for our system, the design requisites, our approach for deployment, and analyze results from real-world field tests. Introduction and Motivation Academic advisors assist students in personal, academic, professional and social matters. Successful advising programs increase student retention, improve graduation rates and help students meet educational goals (Gordon et al. 2011). Advising tasks are identified as prescriptive, providing expert advice, and developmental, where the advisor engages in a mutual learning process with the student, in order to help the student’s problem solving, decision making and evaluations skills (Appleby 2008). Academic institutions are also adopting learningcentered educative advising, to guide students on the philosophy of the curriculum and provide them with the skills needed for long-term educational planning (Melander 2005; Hagen and Jordan 2008). To help advisors manage these tasks, advising research has focused on technologies such as instant messaging, social networking and coursemanagement systems (Leonard 2008; NACADA 2012). We propose the next generation of interactive advising Copyright © 2014, Association for the Advancement of Artificial Intelligence (www.aaai.org). All rights reserved. systems should include a natural language interface to allow students to communicate as freely as they do with their advisors. Such a system would allow students to easily ask a wider range of questions than those in traditional expert-based systems and obtain immediate responses instead of waiting for peers or advisors to reply. This application also responds to a digital generation that thrives on immediate gratification through firsthand capabilities (Prensky 2001; Junco and Mastrodicasa 2007). In essence, the fundamental objective of this work is to provide students with an advising experience that is as close as possible to traditional human interaction.