The Design and Implementation of Chatbot for Student Information and Requests
CHAPTER ONE
OBJECTIVES
The objectives of this project are:
- To analyze users queries and understand users message.
- To provide an answer to the query of the user efficiently and effectively.
- To develop a system which replies using a responsive GUI similar to a real person talking to the user.
CHAPTER TWO
LITERATURE REVIEW
INTRODUCTION
This literature review was carried out mainly to implement chatbot for student information system, how it is designed and implemented in different platforms and its efficiency and effectiveness in use. And to formulate a different approach which will proffer solution to the implementation of chatbots for educational purposes.
A chatbot is a computer software application which simulate a conversation with a user either via speech or voice through messaging applications, websites, mobile apps or telephone. It interacts with the user like normal human-to-human chat. It cannot handle complex human interactions as it is preprogrammed with certain keywords, so it is limited when not fed with the right keywords. With the incorporation of Artificial Intelligence (AI) and Natural Language Processing (NLP) the chatbot is able to handle complex cases of human conversation. This is especially useful in schools to seek information about the school and for teaching purposes.
RELATED WORKS
Some of the existing systems related to this project are reviewed below:
Research developed a chatbot using machine learning model at the back end for processing and training purposes, and NLP (Natural Language Processing & NLU (Natural Language Understanding) for taking and understanding the input. Google Dialog flow was used to achieve this. The limitation of this work is that it was deployed as an android application and it is not available to other OS platforms. Research uses HTML, CSS and PHP to build a web based Chatbot that store new queries in the database. The scope of this work does not include machine learning processing as only the admin provides guidance. In Research a web based chatbot is developed for college for student query using AIML (Artificial Intelligence Modelling
Language). AIML cannot handle all of its backend processing so some other algorithm has not to employed thereby increasing the overall response time. Research proposes an extension to the model of a chatbot called knowie which was developed using Ubuntu Linux, Python, JDK, PyAIML, and MakeAiml. This requires that the students are present in the laboratory to make use of the chatbot. In Research, a chatbot was developed for the windows platform using Java programming language. The limitation of this is that it does not have a database and can only respond to queries that has responses already. No improvement can be made to this chatbot and can only operate on the Windows operating and system. Research proposes a model that has two main phases; knowledge abstraction and response generation and it uses Dialog flow to implement the project. This work is a theoretical solution and the result may prove insufficiently informative to be depended upon. Research develops a Pharmabot using visual C# as its frontend and MS Access as its backend. This work cannot be used over the web as it is designed to be installed on a standalone computer and it does not incorporate artificial intelligence into its processing. Research develops a chatbot with four levels in its architecture; the front office, back office, knowledge base module and e-learning bot module. It’s an easy to use chatbot but gives suggestions not helpful to students and in some cases, a wrong suggestion. Research developed a chatbot prototype to determine the memory retention of students who source answers from chatbot and Google search engine. It was observed that the students had a better memory retention of answers from the chatbot. Research builds a chatbot using Dialog flow and Natural Language Processing (NLP). This research can be deployed to any operating system. Research developed a chatbot that can be accessed via Facebook messenger. This chatbot does not offer backend access to admin to edit unanswered queries and it cannot be updated. Research discusses the issues of chatbot development which are NLP and Machine Learning. Research develop a chatbot using Google owned Dialog flow. This chatbot handles placement activities in professional colleges and reduces physical visit to the institute. Research tested and evaluated a prototype chatbot in a small university setting which was strong in conversational patterns due to NLP but was lost when facing usual conversational pattern. Researc chatbot was developed using AIML for University related Frequently Asked Questions (FAQs). This chatbot does not provide satisfactory answer when a data is missing from the user query.
CHAPTER THREE
DESIGN AND IMPLEMENTATION
INTRODUCTION
This chapter details the chosen methodology used in the project, and the approach chosen for the selected methodology. The design tools, techniques and platforms used in the implementation of the project. The ethical considerations of this project are also observed in this chapter. The requirement analysis and specification of the project are also clearly stated in this chapter.
INTRODUCTION
This chapter talks about the results obtained from the system design and development. This includes software development, testing and evaluating the system performance.
SYSTEM DEVELOPMENT
A web application was developed to host the Chatbot to provide an interface for interaction by the user. The system development can be classified into two phases:
- The frontend
- The backend
CHAPTER FIVE
LIMITATIONS, CONCLUSION AND RECOMMENDATION
LIMITATION
This project stretch it feature to make use of user browser database which is index DB to store chat file for individual user and also restore from it. During the development of this project, the feature was tried but could not be achieve due to the fact that accessing client browser database is front end language query and not backend language query.
Also, due to time constraint some feature like API and Webhook could not be included for connectivity to other chatting messenger like Facebook, Telegram and WhatsApp.
CONCLUSION
The aim of developing a Chatbot web application for student assistance or school service support was achieved. With this Chatbot both student and aspiring student can easily get any information at their finger tip. While it will also reduce the spread of wrong information due to sourcing information from unreliable source which is very common among the student most especially aspiring student.
RECOMMENDATION
Some of the features that can be implemented in future to enhance the performance and operation of the developed system are:
- Addition of language translation
- Addition of voice translation for those who cannot read and write
- Inclusion of Web Sockets. (Web-hook, APIs)
- Geolocation feature.
REFERENCES
- (ICACCI), Udupi, 2017, pp. 1525-1530.
- Aysha Khan, Sakshi Ranka, Chaitali Khakare, Subodh Karve “NEEV: An
- Education Informational Chatbot” International Research Journal of Engineering and Technology (IRJET) e-ISSN: 2395-0056 Volume 6, Issue 4, April 2019.
- Omar Zahour, El Habib Benlahmar, Ahmed Eddaoui, Hafsa Ouchra,
- Oumaima Hourrane “A system for educational and vocational guidance in
- Morocco: Chatbot E-Orientation” International Workshop on Artificial
- Intelligence & Internet of Things (A2IoT) August 9-12, 2020.
- Jagdish Singh, Minnu Helen Joesph and Khurshid Begum Abdul Jabbar
- “Rule-based chabot for student enquiries” International Conference on Computer Vision and Machine Learning: Journal of Physics: Conference
- Series:1228 012060, 2019.
- AM Rahman, Abdullah Al Mamun, Alma Islam “Programming challenges of Chatbot: Current and Future Prospective” 2017 IEEE Region 10
- Humanitarian Technology Conference (R10-HTC), Dec 2017.
- S.S. Ranavare and R. S. Kamath “Artificial Intelligence based Chatbot for
- Placement Activity at College Using DialogFlow” Our Heritage Journal
