Chatbot

About: Chatbot is a research topic. Over the lifetime, 2415 publications have been published within this topic receiving 24372 citations. The topic is also known as: IM bot & AI chatbot.

Improve the Security of Social Media Accounts

Abstract: The task of improving of security level of accounts in such social media as Facebook, YouTube and Instagram is considered in the paper. A mathematical model of formation of social media security level indicator is built. According to the obtained mathematical model, a chatbot is developed. The developed chatbot allows to estimate the security level of a social media account. If necessary, it formulates recommendations concerning improvements on social media account security level.

In-the-wild chatbot corpus: from opinion analysis to interaction problem detection

Abstract: The past few years have seen growing interests in the development of online virtual assistants. In this paper, we present a system built on chatbot data corresponding to conversations between customers and a virtual assistant provided by a French energy supplier company. We aim at detecting in this data the expressions of user's opinions that are linked to interaction problems. The collected data contain a lot of "in-the-wild" features such as ungrammatical constructions and misspelling. The detection system relies on a hybrid approach mixing hand-crafted linguistic rules and unsupervised representation learning approaches. It takes advantage of the dialogue history and tackles the challenging issue of the opinion detection in "in-the-wild" conversational data. We show that the use of unsupervised representation learning approaches allows us to noticeably improve the performance (F-score = 74.3%) compared to the sole use of hand-crafted linguistic rules (F-score = 67,7%).

Use of chatbots for user service in higher education institutions

Abstract: This paper arises from the need to have new tools or communication channels that allow users to answer questions or concerns about different fields at the university level. In particular, the results of the analysis of the use of three chatbots, implemented in a higher education institution, are presented. The results obtained from the surveys, considering the usability of the chatbot and the accuracy of the responses, show that the level of satisfaction of using the chatbots is high, therefore, it is recommended to use this type of systems for the attention of users.

Capabilities of Chatbots and Its Performance Enhancements in Machine Learning

Abstract: To keep in pace with ever-increasing customer demands, providing instant and useful responses is a prominent need of service providers. Latest technical developments have led to the advent of a faster, easier solution: chatbot. It is an artificial intelligence-based simulation of human conversation to automate customer interactions, thereby reducing manual effort. Not necessarily limited to answering simple product-related queries, chatbots can provide complex predictive analysis within limited response time, by the help of machine learning. Creating a chatbot has become simplistic enough, even for any non-technical person. It can be configured and integrated into any messenger within an organization or social network. This paper discusses the capabilities of chatbots and the enhancements in their performance by the contribution of machine learning.

Applications of Sequence to Sequence Models for Technical Support Automation

Abstract: Juniper Networks, Inc. offers hardware products and software services to its enterprise customers. Due to the nature of it’s business, Juniper Networks, Inc. is deeply invested in providing the best customer support and as part of the support automation team, our goal is to optimize the company’s efforts towards it. For this purpose, alongside other initiatives, we leverage deep learning based sequence to sequence models wherever we see fit. In this paper, we discuss two such models: a conversational chatbot to help answer some technical questions for our customers, and a text summarizer to condense the large text in our support tickets and other articles. These two models are designed using bi-directional recurrent neural network (Bi-RNN) architectures for content understanding and were customized to fit the domain-specific nature of our data. First, we discuss our efforts towards data preparation. Then, we explain our model design, customization and evaluation mechanisms. Finally, we provide the preliminary results and share the potential impact our models will have on our business. Our initial results have BLEU score of 0.21 for text summarizer which is 16% better than our baseline model. Our chatbot passed the eye-tests of our subject matter experts.