Criteria Selection and Comparative Analysis of Popular Chatbot Frameworks (Dialog flow, Microsoft Bot Framework, IBM Watson Assistant and Rasa) For Implementation in Libraries: a Systematic Literature Review

Abstract

ABSTRACT Chatbots are increasingly popular in various fields, including in libraries, to improve services and interactions with users. In choosing a chatbot for libraries, proper criteria are needed. Some common chatbot frameworks are Dialogflow, Microsoft Bot Framework, IBM Watson Assistant, and Rasa, which have advantages and disadvantages in the library context. This research conducts a systematic literature review on the selection criteria and comparison of popular chatbot frameworks such as Dialogflow, Microsoft Bot Framework, IBM Watson Assistant, and Rasa in library implementation. The research method used a systematic literature review from sources such as IEEE, Proquest, and ScienceDirect. The keywords used were ("Chatbot" OR "Bot" OR "Conversational agent" OR "Virtual assistant") AND ("Dialogflow" OR "IBM Watson Assistant" OR "Microsoft Bot Framework" OR "Rasa"). The results show that the criteria in chatbot selection include Natural Language Understanding (NLU) pipeline customization capabilities, ease of use, integration with Machine Learning and Natural Language Processing, integration capabilities with communication channels, natural language understanding capabilities, validation with automated user story extraction systems, flexibility in development, and tools for natural language processing and machine learning. Although no articles specifically addressing chatbots were found in the library, this research provides an overview of chatbot selection criteria and provides information on the advantages and disadvantages of each chatbot framework as outlined in the results and discussion table. In conclusion, although research questions RQ1 and RQ2 cannot be answered due to the lack of specific articles about chatbots in libraries, this research provides an overview of chatbot selection criteria and can provide an understanding of the advantages and disadvantages of existing chatbot frameworks...   ABSTRAK Chatbot semakin populer di berbagai bidang, termasuk di perpustakaan, untuk meningkatkan layanan dan interaksi dengan pengguna. Dalam memilih chatbot untuk perpustakaan, kriteria yang tepat diperlukan. Beberapa framework chatbot umum adalah Dialogflow, Microsoft Bot Framework, IBM Watson Assistant, dan Rasa, yang memiliki kelebihan dan kekurangan dalam konteks perpustakaan. Penelitian ini melakukan tinjauan literatur sistematis tentang kriteria pemilihan dan perbandingan framework chatbot populer seperti Dialogflow, Microsoft Bot Framework, IBM Watson Assistant, dan Rasa dalam implementasi perpustakaan. Metode penelitian menggunakan tinjauan literatur sistematis dari sumber seperti IEEE, Proquest, dan ScienceDirect. Kata kunci yang digunakan adalah ("Chatbot" OR "Bot" OR "Conversational agent" OR "Virtual assistant") AND ("Dialogflow" OR "IBM Watson Assistant" OR "Microsoft Bot Framework" OR "Rasa"). Hasil penelitian menunjukkan bahwa kriteria dalam pemilihan chatbot mencakup kemampuan penyesuaian pipeline Natural Language Understanding (NLU), kemudahan penggunaan, integrasi dengan Machine Learning dan Natural Language Processing, kemampuan integrasi dengan saluran komunikasi, kemampuan memahami bahasa alami, validasi dengan sistem ekstraksi cerita pengguna otomatis, fleksibilitas dalam pengembangan, dan alat untuk pemrosesan bahasa alami dan pembelajaran mesin. Meskipun tidak ditemukan artikel yang secara khusus membahas chatbot di perpustakaan, penelitian ini memberikan gambaran umum tentang kriteria pemilihan chatbot dan memberikan informasi tentang kelebihan dan kekurangan masing-masing framework chatbot seperti yang diuraikan dalam tabel hasil dan pembahasan. Dalam kesimpulannya, meskipun pertanyaan penelitian RQ1 dan RQ2 tidak dapat terjawab karena kurangnya artikel yang spesifik tentang chatbot di perpustakaan, penelitian ini memberikan gambaran umum tentang kriteria pemilihan chatbot dan dapat memberikan pemahaman tentang kelebihan dan kekurangan framework chatbot yang ada.