Chatbot Datascience Proposal, Schemes and Mind Maps of Computer Science

Download Chatbot Datascience Proposal and more Schemes and Mind Maps Computer Science in PDF only on Docsity! Section 1: Student Details Full name: Student number: Award / course: BSc Computer Science Email address: Supervisor: Date of submission: 31/12/2020 1 Table of Contents SECTION 1: STUDENT DETAILS. . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 1 TABLE OF CONTENTS. . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 2 SECTION 2 STATEMENT OF PROJECT. . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 3 2.1 PROJECT TITLE . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 3 2.2 ACADEMIC QUESTION. . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 3 2.3 UNIVERSITY ENQUIRY CHATBOT (PROPOSED) TO BE DEVELOPED. . . . . . 3 SECTION : 3 PROJECT PROPOSAL. . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 4 3.1 INTRODUCTION. . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 4 3.2 INITIAL RESEACH INTO SOURCES OF INFORMATION. . . . . . . . . . . . . . . . . 5 3.3 UNIVERSITY CHATBOT (proposed). . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 9 3.4 REFERENCES. . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 10 SECTION : 4 ADDITONAL SOURCES OF INFORMATION. . . . . . . . . . . . . . . . . . . 12 4.1 RESOURCES. . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 12 2 AI-powered chatbots are motivated by the need of traditional websites to provide a chat facility where a bot is required to be able to chat with user and solve queries. When live agent can handle only two to three operations at a time, chatbots can operate without an upper limit which really scales up the operations. Also, if any school or business is receiving lots of queries, having a chatbot on a website takes off the load from support team. Having a chatbot clearly improves the response rate compared to human support team. In addition, since millennials prefer live chats over a phone call, they find a chatbot, which provide a highly interactive marketing platform, very attractive. Furthermore, a chatbot can automate the repetitive tasks. There can be some scenarios where a business or school receives same queries in a day for many times and support team must respond to each query repetitively. Lastly, the most important advantage of having a chatbot is that it is available 24/7. No matter what time it is, a user can get a query solved. All these advantages of a chatbot constitute the motivation to implement a University Enquiry Chatbot 3.2 Initial Research into source of Information In order to understand the requirement of a chatbot, consider an example of Amazon Shopping App. In this app, when a customer buys an item, he/she does not have any information about how to return the item. To get this information, the customer must call and wait to talk to customer representative for a long time. However, this whole process is tedious for a customer. Hence, Amazon created a chatbot to answer simple queries of customers. Similarly, the university Enquiry Chatbot is designed to help students to get their queries solved on a fingertip. The study proposes that “there is a need to understand and consider the stability, scalability, and flexibility issues along with high level of intention of a human language”. Hence, for implementing a chatbot that handles complicated queries, the sentiment analysis is incorporated into University Enquiry Chatbot. Sentiment analysis aims to obtain writer’s feelings expressed in positive, negative or neutral comments. Based on sentiment analysis, the bot is trained to have empathy while answering to the user. For example, if a user says, “I am sad today.” then bot should reply to it with some empathy like “I’m sorry to hear that, how can I help you today?” and not just reply the standard message like “Sorry did not understand your question.” Another downside which was found during a research on 5 chatbot is that bots are created in such way that they follow a specific route and mostly all of them fails to satisfy anything outside of the previously defined scripts. This means that if they are not part of a predefined scripts, a significant number of the bots will fail in understanding even the most fundamental kind of queries, which results in a repeating and horrendous experience. To resolve this issue, active learning can be introduced to the system to make probabilistic assessments and provide autonomous responses to the users . Active learning is an algorithm which interactively queries user to obtain the desired output. Whenever a user asks anything which is outside of the script the chatbot will ask questions to the user by giving two to three options and based on the user’s input, the bot returns the answer to that query. This whole learning process is called as active learning System design of College Enquiry Chatbot consists of integration of multiple technologies. This system makes use of NodeJS for backend and ReactJS for frontend. Microsoft Azure provides services like Cognitive Service, Bot Service and Web Apps. Cognitive services consist of Text Analytics, LUIS and QnA Maker. The bot service is used to create the bot application on Azure. In addition, Web Apps are used to host the application on Microsoft Azure. System uses Mongo DB to store the conversations history. Figure: 2 show a System Design 6 Microsoft Azure Microsoft Azure provides cloud services to build, manage, and deploy applications on a cloud network which helps organization to meet their business needs using their favourite tools and frameworks. College Enquiry Chatbot uses all the services shown in Figure 2 which are provided by Microsoft Azure. Azure Bot Service Azure bot service is a service provided by Microsoft Azure which builds and artificial intelligence (AI) chatbot. It offers the ability to add intelligent agents that can do conversations with users without having to commit the resources to develop one’s own AI . Azure Web App I have used Azure web app to host my bot application build by Azure bot service. Azure Web App are the web applications which are hosted on Microsoft Azure cloud without any programming language barrier. Since it is hosted on the cloud, infrastructure maintenance is not needed to host the applications. It also provides various features like auto scaling, automated deployment and supports both Windows and Linux environments . Azure Cognitive Services Azure Cognitive services are used to add intelligence to the bots by adding features such as sentiment analysis and language understanding which help in analysing user's queries. These services can be added to an existing bot by adding service calls to the Microsoft's SDK to get the desired results. College Enquiry Chatbot utilizes Text Analytics, LUIS, and QnA Maker services which are part of cognitive services and use natural language processing (NLP) for different purposes. Sentiment Analysis Figures 3 and 4 show how a bot is answering the irrelevant questions of a user for which normal bots are not showing any kind of empathy. To make the bot to be able to respond these kinds of responses, the bot is trained with the chitchat integration which is provided by QnA Maker in which there are lots of questions and answers pairs are available. 7 3.4 References: [1] "Chatbot", en.wikipedia.org, 2010. [Online]. Available: https://en.wikipedia.org/wiki/Chatbot. [Accessed Jul. 10, 2018]. [2] "Chatbot: What is Chatbot? Why are Chatbots Important? -", Expertsystem.com, 2018. [Online]. Available: https://www.expertsystem.com/chatbot/. [Accessed Sep. 11, 2018]. [3] "Amazon.com: Online Shopping for Electronics, Apparel, Computers, Books, DVDs & more", Amazon.com, 2017. [Online]. Available: https://www.amazon.com/. [Accessed Sep. 12, 2018]. [4] "Amazon Alexa - Build for Amazon Echo Devices", Developer.amazon.com, 2017. [Online]. Available: https://developer.amazon.com/alexa. [Accessed Sep. 12, 2018]. [5] "Meet Erica, Your Financial Digital Assistant From Bank of America", Bank of America, 2018. [Online]. Available: https://promo.bankofamerica.com/erica/. [Accessed Sep. 12, 2018]. [6] C. Doug Gross, "Facebook: Get Messenger app or else - CNN", CNN, 2014. [Online]. Available: https://www.cnn.com/2014/07/29/tech/socialmedia/facebook-messenger/ index.html. [Accessed Sep. 12, 2018]. [7] A. Storman, "5 Chatbot Challenges and How to Overcome Them", Chatbots Magazine, 2016. [Online]. Available: https://chatbotsmagazine.com/5-chatbotchallenges-and-how-to- overcome-them-caccc3a26d7c. [Accessed Sep. 11, 2018]. [8] A. M. Rahman, A. A. Mamun and A. Islam, "Programming challenges of chatbot: Current and future prospective," in 2017 IEEE Region 10 Humanitarian Technology Conference (R10- HTC), Dhaka, 2017. [9] "Problems with Chatbots Today - Attunix", Attunix, 2018. [Online]. Available: 10 https://attunix.com/problems-chatbots-today/. [Accessed Sep. 11, 2018]. [10] "Azure Bot Service - chatbot | Microsoft Azure", Azure.microsoft.com, 2017. [Online]. Available: https://azure.microsoft.com/en-us/services/bot-service/. [Accessed Jul. 22, 2019]. [11] "LUIS (Language Understanding) – Cognitive Services – Microsoft Azure", Luis.ai, 2017. [Online]. Available: https://www.luis.ai/home. [Accessed Jul. 15, 2018]. [12] "QnA Maker", Qnamaker.ai, 2016. [Online]. Available: https://www.qnamaker.ai/. [Accessed Jul. 17, 2018]. [13] "What is Azure Bot Service? - Definition from WhatIs.com", WhatIs.com, 2018. [Online]. Available: https://whatis.techtarget.com/definition/Azure-Bot-Service. [Accessed Jan. 17, 2019]. [14] "Azure App Service Documentation - Tutorials, API Reference", Docs.microsoft.com, 2015. [Online]. Available: https://docs.microsoft.com/enus/azure/app-service/. [Accessed Dec. 17, 2018]. [15] "Cognitive Services | Microsoft Azure", Azure.microsoft.com, 2017. [Online]. Available: https://azure.microsoft.com/en-us/services/cognitive-services/. [Accessed Dec. 22, 2018]. 11 SECTION : 4 ADDITONAL SOURCES OF INFORMATION 4.1 Resources: Mauldin, Michael L.,” CHATTERBOTS, TINYMUDS, and the Turing Test: Entering the Loebner Prize Competition.” Proceedings of the 12th National Conference on Artificial Intelligence (Seattle, WA, USA, July 31 – August 4, 1994), Vol. 1. p. 16–21. [2] Shawar, Bayan Abu and Eric Atwell, „Using dialogue corpora to train a chatbot”. Proceedings of the Corpus Linguistics 2003 conference (Lancaster, 28-31 March 2003) Lancaster University, 2003, p. 681–690. [3] Britz, Denny, „Deep Learning for Chatbots. Part 1”. WILDML. Artificial Intelligence, Deep Learning, and NLP. 6 April 2016, http://www.wildml.com/2016/04/deep-learning-for- chatbots-part1-introduction/ [4] Bradford, Laurence, „How Chatbots Are About To Change Communication”, Forbes.com, 25 July 2017, https://www.forbes.com/sites/laurencebradford/2017/07/24/howchatbots- are-about-to-change-communication/#258058164aa8 [5] Petronzio, Matt, „A Brief History of Instant Messaging”, Mashable.com, 25 October 2012, http://mashable.com/2012/10/25/instant-messaginghistory/#XnMxDUiwxPqR 12