1 Introduction
-
RQ1: What are the current AI models and algorithms that deployed into the Advising chatbots?
-
RQ2: What are the current Advising chatbots services at universities?
-
RQ3: How do AI conversational advisers support high school students?
2 Methodology
2.1 Approach
2.2 Resources
Database | Number of Studies |
---|---|
WorldCat.org | 87 |
Academic Search Complete | 10 |
Computers & Applied Sciences Complete | 12 |
ScienceDirect | 2 |
ProQuest Central | 13 |
ABI/INFORM Global | 4 |
Electronic Books (27) | 27 |
SAGE Journals (1) | 1 |
Total | 156 |
Google Scholar | 6 |
All Articles | 162 |
2.3 Search Criteria
code | Search Category | Criteria |
---|---|---|
A | Chatbot | (chatbot OR dialogue OR “conversational AI” OR “conversational agent” OR “digital assistant” OR “Virtual Assistant”) |
B | AI-based Approach | (“Machine Learning” OR “Deep Learning” OR “Neural network” OR “Artificial Intelligence”) |
C | Education | (education OR academic OR adviser OR advisor OR advising OR school OR “high school” or “college” OR “university” OR “Universities” OR “students” OR “students”) |
Formula= | “A” AND “B” AND “C” ti:(chatbot OR dialogue OR “conversational AI” OR “conversational agent” OR “digital assistant” OR “Virtual Assistant”) AND ti:(“Machine Learning” OR “Deep Learning” OR “Neural network” OR “Artificial Intelligence”) AND ti:(education OR academic OR adviser OR advisor OR advising OR school OR “high school” or “college” OR “university” OR “Universities” OR “students”) |
2.4 Identification
2.5 Screening and Eligibility
2.6 Excluded Strategy
2.7 Included Strategy
Article Name | Author | Result | Goal | Evaluation/Dev | Academic Service | Target audience | AI-Approach |
---|---|---|---|---|---|---|---|
Artificial Intelligence Based University Chatbot using Machine Learning | Khan et al. (2021) | The results show that the Random Forest is outperform for the proposed study | Supporting people which are visiting the admission office this will also decrease the traffic of the admission office | Evaluating the Models | University Admission | Parents and Prospected students at universities | Supervised Machine Learning (DT, RF, SVM) |
Implementation of a Virtual Assistant for the Academic Management of a University with the Use of Artificial Intelligence | Villegas-Ch et al. (2021) | The results show an increasing number of the enrolled students in the training program since students they have more knowledge about the program | Providing more information on an academic courses at universities and reducing the administrative budgets | Evaluated by using the survey to the training programs students | Admission section-training programs offered by the university | College students | Language Understanding (LUIS) is a cloud-based conversational AI |
Engaging Students With a Chatbot-Based Academic Advising System | Kuhail et al. (2022) | that helps students with prescriptive academic inquiries | Academic Advising | Current university students | |||
A Chatbot to Support Basic Students Questions | Santana et al. (2021) | Delivering a high accuracy in the classification of enquiries intention The chatbot is able to answer the most FAQ | Helping new students in the general administrative procedures and processes | Developing a new model (chatbot) | Academic Advising- | Freshmen students | NLP and Machine Learning |
Artificial Intelligence based Chatbot for Placement Activity at College Using DialogFlow | Ranavare & Kamath (2020) | This Chatbot is integrated to institute’s website by clicking the Integrations choice in the left panel to generate a web demo for present agent and then press the Web Demo tile button | This agent provides information about placement activities to students | Developing a model/Integration | Internship (placement activites) service | Current students in universities (Internship) | DialogFlow and Natural Language Processing (NLP) |
Jooka: A Bilingual Chatbot for University Admission | El Hefny et al. (2021) | The System Usability Scale (SUS) and Chatbot Usability Questionn (CUQ) were used to evaluate it terms of usability acceptable value is <62.6” | A bilingual chatbot for supporting students and German University in Cairo (GUC)’ staff to enhance their admission process | Developing a chatbot | University Admission | Prospected Students (High School) | (Dialogflow ES) and Amazon Web Services (AWS) |
College Enquiry Chatbot using Rasa Framework | Meshram et al. (2021) | It’s done by having a confusion matrix and performance measures like Precision, Accuracy & F1 Score and the results 0.628, 0.725 and 0.669 | Answering students queries about any admissions-related question | Developing a chatbot | University Admission | New students at Universities and prospected Students | Natural Language Understanding with RSA NLU-Open Resource Technology |
CollegeBot: A Conversational AI Approach to Help Students Navigate College | Daswani et al. (2020) | The semantic (similarity mode) outperforms seq2seq model even though the seq2seq model is faster than semantic similarity | To assist visitors of a university’s web site to locate answers to their queries | Evaluating two algorithms for training Chatbot & model proof-of-concept prototype to demonstrate adopted by other colleges | Students orientations | Prospected and current students (All university’s website visitors) | NLP (Semantic Similarity) and RNN-based Sequence-to-Sequence (seq2seq) |
Bilingual AI-Driven Chatbot for Academic Advising | Bilquise et al. (2022) | The chatbot engine determines the user’s intent by processing the input and retrieving the most correct response that matches the intent with an accuracy of 80% in English and 75% in Arabic | Supporting current students in universities by answering to their academic questions such as the requirement courses, electives and GPA | Developing a bilingual chatbot (Arabic/ English) | Academic Advising-College students | Current students in Colleges | Neural network and Natural Language (NLP) technologies |
Indonesian chatbot of university admission using a question answering system based on sequence-to-sequence model | Chandra, Y. W., & Suyanto, S. (2019) | Using the Metric of BLUE score: 44.6 | Customer service-Admission office by integrating it with Whatsapp instant messaging | Developing a chatbot in Telekom University in Indonesia | Students Admission | New Students | Seq2Seq-bidirectional LSTM with Attention in the Encoder-Decoder- |
Developing a Chatbot system using Deep Learning based for Universities consultancy | Le-Tien et al. (2022) | The results achieve 89% F1-score of 3 classes of the Text Classification in Deep Learning | Advising the current students toward their academic plan | A Proof of Concept to the Ho Chi Minh City University of Technology (HC-MUT) | Academic Advising | Current Students | Bidirectional-LSTM with Attention mechanism |
2.8 Literature Taxonomy
3 Results and Discussion
3.1 Advising Chatbots AI Architecture
-
RQ1: What are the current AI models and algorithms that deployed into the Advising chatbot?
3.1.1 Deep Learning
3.1.2 Hybrid Learning
3.1.3 Open-Source Tools for Customizing AI Chatbots
3.2 The Goals of the Advising Chatbots.
-
RQ2: What are the current Advising chatbots services at universities?
-
RQ3: How do AI conversational advisers support high school students?