Müşteri Hizmetleri Yönetiminde Yapay Zeka Temelli Chatbot Geliştirilmesi

İşeri, İsmail; Aydın, Özkan; TUTUK, Kaan

doi:10.31590/ejosat.1025380

Cited by 6 publications

(3 citation statements)

References 12 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Chatbots can be used for many different applications. For example, a chatbot design consisting of 3 layers that analyzes and corrects Syntax errors in the Turkish language has been proposed [15]. In another study, a chatbot was proposed to be used in customer service management using the BERT model [16].…”

Section: Literature Reviewmentioning

confidence: 99%

Ensemble Learning Approach to Chatbot Design Based on Paraphrase Detection

KESGİN,

ÖZTUNÇ,

DİRİ

2023

Kocaeli Journal of Science and Engineering

View full text Add to dashboard Cite

Many companies are setting up call centers to ensure the satisfaction of their customers. The call centers are mainly used by the customers to collect information about their products or services. However, it is quite costly to provide 24-hours service. Therefore, companies aim to develop a chatbot to reduce the need for the call center. In this paper, we propose a ensemble chatbot design based on paraphrase detection. Our algorithm and does not require a large number of instances or labels and it can work on small data sets, for example an existing FAQ. Chatbots perform best when they are domain specific. We used publicly available data from the websites of major telecommunication companies. We propose an ensemble chatbot design based on paraphrase detection. The ensemble model improves the success by 10 % compared to the single best model. Our proposed ensemble chatbot design has 84.54 % top-3 and 70.10 % top-1 accuracy.

show abstract

Section: Literature Reviewmentioning

confidence: 99%

Ensemble Learning Approach to Chatbot Design Based on Paraphrase Detection

KESGİN,

ÖZTUNÇ,

DİRİ

2023

Kocaeli Journal of Science and Engineering

View full text Add to dashboard Cite

show abstract

“…With a chatbot, users can conduct a humanlike conversation with a bot by using textual or auditory methods (Fleischner and Grad, 2019) and the software programs enable chatbots to produce appropriate responses depending on the communications with customers with the help of machine learning and deep learning. Natural language processing, predictive analytics and sentiment analysis are the outcomes of that process that the software learns from the past dialogues with the customers (through customer calls or Whatsapp dialogues) and produce appropriate responses over time (Robinson, et al, 2017, Nguyen, 2020, İşeri, Aydın and Tutuk, 2021. There are three kinds of Chatbots -informational (informs the customers about FAQ, push notifications), transactional (with a user account, customers can make a transaction like booking a hotel), advisory (self-learning chatbots that comprehend the information got from the customer interactions and predict the next moves of customers) (Robinson, et al, 2017).…”

Section: Introductionmentioning

confidence: 99%

What are the Drivers of Using Chatbots in Online Shopping A Cross-Country Analysis

Çelik¹,

Hüseyinli²,

Can³

2022

isarder

View full text Add to dashboard Cite

Purpose –Technological evolutions have made the products & services almost identical, and experience becomes the key differentiation tool for competition. Especially the service companies design customer journey to create memorable, amusing, and recommendable experiences. AI chatbots help enrich the customer experience and save cost and time with its automated structure. With this study, it’s aimed to discover the determinants of young consumers’ intention to use chatbots in e-shopping comparatively in Turkey and Azerbaijan. Design/methodology/approach –The research model was based on Technology Acceptance Model and U&G Theory. The data gathered via an online questionnaire; 300 responses were analyzed using SEM. Findings:The findings showed that the perceived ease of use didn’t positively affect the perceived usefulness of chatbots in Turkish sample; however, the communication competence positively affects perceived usefulness, and the entertainment positively affects theattitude towards chatbots. For Azerbaijani sample, the research model was wholly confirmed with the causal relationships among all variables. Discussion –This article clarifies underlying motives for usage intention during online shopping of university students living in different countries and provides practical implications about the consumers’ expectancies regarding chatbots during e-shopping. As a gratification factor, entertainment is an important determinant to experience and create a positive attitude towards chatbot. Designing an easy-to-use chatbot is not adequate to encourage the consumers to use chatbot but the chatbot should have the ability to solve not only standard problems but also particular problems faced by the consumers. In online shopping via chatbots consumers’ fears and reservations about privacy concern can be eliminated by offering safer payment options like cash/credit card at the door.

show abstract

“…A generative pretrained transformer (ChatGPT) is an artificial intelligence (AI) chatbot that understands and generates human language with exceptional sophistication, accuracy, and usability 1. Chatbots are AI software programs created to interact with users through text or voice that are capable of performing various tasks without human assistance 2. ChatGPT, developed by OpenAI, is one of the largest language models with more than 175 billion parameters 3…”

mentioning

confidence: 99%

Reliability and Quality of the Nursing Care Planning Texts Generated by ChatGPT

Dağci,

Çam,

Dost

2023

Nurse Educator

View full text Add to dashboard Cite

Background: The research on ChatGPT-generated nursing care planning texts is critical for enhancing nursing education through innovative and accessible learning methods, improving reliability and quality. Purpose: The aim of the study was to examine the quality, authenticity, and reliability of the nursing care planning texts produced using ChatGPT. Methods: The study sample comprised 40 texts generated by ChatGPT selected nursing diagnoses that were included in NANDA 2021-2023. The texts were evaluated by using a descriptive criteria form and the DISCERN tool to evaluate health information. Results: DISCERN total average score of the texts was 45.93 ± 4.72. All texts had a moderate level of reliability and 97.5% of them provided moderate quality subscale score of information. A statistically significant relationship was found among the number of accessible references, reliability (r = 0.408), and quality subscale score (r = 0.379) of the texts (P < .05). Conclusion: ChatGPT-generated texts exhibited moderate reliability, quality of nursing care information, and overall quality despite low similarity rates.

show abstract

Müşteri Hizmetleri Yönetiminde Yapay Zeka Temelli Chatbot Geliştirilmesi

Cited by 6 publications

References 12 publications

Ensemble Learning Approach to Chatbot Design Based on Paraphrase Detection

Ensemble Learning Approach to Chatbot Design Based on Paraphrase Detection

What are the Drivers of Using Chatbots in Online Shopping A Cross-Country Analysis

Reliability and Quality of the Nursing Care Planning Texts Generated by ChatGPT

Contact Info

Product

Resources

About