A New Chatbot for Customer Service on Social Media

Xu, Anbang; Liu, Zhe; Guo, Yufan; Sinha, Vibha Singhal; Akkiraju, Rama

doi:10.1145/3025453.3025496

Cited by 404 publications

(226 citation statements)

References 7 publications

Supporting

Mentioning

195

Contrasting

Unclassified

Order By: Relevance

“…Some of the core areas that Deep learning is considered to give solutions for signal processing [26], medical image recognition [27], data mining [28], robotics [29] etc. This helps deep learning to find applications from industries such as banking [30], customer services [31], retail, defence [32], healthcare [33] etc.…”

Section: Fig3 Time Line Of Deep Learningmentioning

confidence: 99%

Diving Deep into Deep Learning: History, Evolution, Types and Applications

Shetty*¹,

C.A²,

Varma³

et al. 2020

IJITEE

View full text Add to dashboard Cite

Although Machine Learning (ML) has become synonymous for Artificial Intelligence (AI); recently, Deep Learning (DL) is being used in place of machine learning persistently. If statistics is grammar and machine learning is poetry then deep learning is the creation of Socrates. While machine learning is busy in supervised and unsupervised methods, deep learning continues its motivation for replicating the human nervous system by incorporating advanced types of Neural Networks (NN). Due to its practicability, deep learning is finding its applications in various AI solutions such as computer vision, natural language processing, intelligent video analytics, analyzing hyperspectral imagery from satellites and so on. Here we have made an attempt to demonstrate strong learning ability and better usage of the dataset for feature extraction by deep learning. This paper provides an introductory tutorial to the domain of deep learning with its history, evolution, and introduction to some of the sophisticated neural networks such as Convolutional Neural Network (CNN) and Recurrent Neural Network (RNN). This work will serve as an introduction to the amazing field of deep learning and its potential use in dealing with today’s large chunk of unstructured data, that it could take decades for humans to comprehend and extract relevant information.

show abstract

Section: Fig3 Time Line Of Deep Learningmentioning

confidence: 99%

Diving Deep into Deep Learning: History, Evolution, Types and Applications

Shetty*¹,

C.A²,

Varma³

et al. 2020

IJITEE

View full text Add to dashboard Cite

show abstract

“…Chatbots have been widely used in various applications such as health [4], education [5] and customer service [6]. The research that developed the chatbot application for city citizen interaction media [7], stated that chatbots provide convenience to users because users do not have to do a long order of commands.…”

Section: Related Workmentioning

confidence: 99%

Keystroke-Level Model to Evaluate Chatbot Interface for Reservation System

Supriyanto¹,

Prahara²,

Saputro³

2019

EECSI

View full text Add to dashboard Cite

The tour package reservation system is an important part of improving tourism services. Reservations must be able to meet the information needs of prospective customers and can serve the desired tour package bookings. A reservation system is usually a form that must be filled in sequence by prospective visitors. This paper discusses the evaluation of the application of the chatbot interface on the reservation system with the keystroke-level model. Changing the interaction design that previously did the task fills out the form into a conversation interaction. The aim is to increase the speed of the ordering process through the system. Prospective visitors do not need to fill in the form, they only need to have a conversation with the system while entering the order data. The evaluation results using the keystroke-level model show that the chatbot interface can increase the speed of the process by shortening steps.

show abstract

“…In [15] the authors consider how a chatbot can produce responses using deep learning and so-called LSTM cells in particular. They had access to 1 million twitter conversations from over 60 different brands.…”

Section: Background and Related Workmentioning

confidence: 99%

Towards Open Domain Chatbots—A GRU Architecture for Data Driven Conversations

et al. 2018

View full text Add to dashboard Cite

Understanding of textual content, such as topic and intent recognition, is a critical part of chatbots, allowing the chatbot to provide relevant responses. Although successful in several narrow domains, the potential diversity of content in broader and more open domains renders traditional pattern recognition techniques inaccurate. In this paper, we propose a novel deep learning architecture for content recognition that consists of multiple levels of gated recurrent units (GRUs). The architecture is designed to capture complex sentence structure at multiple levels of abstraction, seeking content recognition for very wide domains, through a distributed scalable representation of content. To evaluate our architecture, we have compiled 10 years of questions and answers from a youth information service, 200083 questions spanning a wide range of content, altogether 289 topics, involving law, health, and social issues. Despite the relatively open domain data set, our architecture is able to accurately categorize the 289 intents and topics. Indeed, it provides roughly an order of magnitude higher accuracy compared to content recognition techniques, such as SVM, Naive Bayes, random forest, and K-nearest neighbor, which all seem to fail on this challenging open domain dataset.

show abstract

A New Chatbot for Customer Service on Social Media

Cited by 404 publications

References 7 publications

Diving Deep into Deep Learning: History, Evolution, Types and Applications

Diving Deep into Deep Learning: History, Evolution, Types and Applications

Keystroke-Level Model to Evaluate Chatbot Interface for Reservation System

Towards Open Domain Chatbots—A GRU Architecture for Data Driven Conversations

Contact Info

Product

Resources

About