Beyond the Scene: A Comparative Analysis of Two Storytelling-based Conversational Agents
Jackylyn L. Beredo, Ethel Ong · 2021
Advances in conversational interfaces have facilitated the widespread use of chatbots in assisting humans in their daily lives such as in retail services, healthcare, and education. With the use of Natural Language Processing techniques (NLP), chatbots can leverage on storytelling strategies to engage children in meaningful conversations to narrate and share their stories. In this paper, we compared two existing conversational storytelling agents, Orsen and EREN, by analyzing the dialog logs to examine children’s engagement when sharing their stories with these agents. Taking three dimensions - language production, flow maintenance, and affect; into consideration, results show that the ability of EREN to recognize emotions expressed in the child’s input text can encourage the children to be more open to sharing their stories. Even though the agent cannot generate affect-rich responses, its ability to recognize the emotions made children feel thankful and appreciative of the agent for listening.