Enhancing Conversational Agents with Empathic Abilities

Emotionally Intelligent Chatbots: A Systematic Literature Review

“…Recent technological advances have made chatbots increasingly feasible to deliver information to various To build a chatbot that captures the emotions of patients during interaction and accordingly updates human therapists to provide timely care 2 [39] To generate affective responses in an open-domain chatbot by using a three-method approach in an LSTM conversational model 3 [60] To develop an empathetic chatbot that generates responses based on the user's emotional state and the context of the message 4 [47] To incorporate emotional content into the response generation process to make chatbot responses more emotionally sound 5 [64] To produce an affect-driven dialog system that generates multiple diverse emotional responses and ranks them based on emotion 6 [77] To extract the affect category of the input text using the Linguistic Inquiry and Word Count (LIWC) and generate grammatically correct responses embedded with emotion 7 [81] To develop an embodied conversational agent that responds based on user profiles and emotional content 8 [69] To predict the emotional state of the sender based on historical responses and accordingly generate an emotionally appropriate response 9 [82] To build a voice-based conversational agent that embeds responses with emotion 10 [8] To develop a novel tone-aware chatbot that generates toned responses to user requests on social media 11 [71] To embed emotions in the dialog based on input emotion and to tackle the problem of generic responses that are not emotionally intelligent…”

“…A large number of studies (n = 14) focus on accurately detecting the emotion of the input message. While some studies predicted the input emo-tion using a classifier [60,61], several studies argue that emotions are complex and cannot be captured by a coarsegrained emotion label. To that effect, some studies predict the emotion by applying the principle of Valence and Arousal (VA) to embed affective meaning for each word in the input message [47,62,63].…”

“…Ghosh et al [77] extended the LSTM language model trained in a conversational speech corpus to generate text enriched in emotion. In another study, Casas et al [60] attempt to understand the context and implicit emotions expressed in input data to generate empathetic responses.…”

“…The model utilizes an independently parameterized transformer decoder with a metalistener to fuse listeners' information and produce an empathetic response. Casas et al [60] used a pretrained DeepMoji Dai-lyDialog dataset to build an emotion classifier using a labeled training set to predict emotional states in text-based messages. Furthermore, Griol et al [81] combine information from the user profiles with emotional content extracted from 14 Human Behavior and Emerging Technologies the user's utterances and apply an emotional recognizer in the dialog manager to choose an adapted system response.…”

Voice Assistant-Based CBT for Depression in Students: Effects of Empathy-Driven Dialog Management

“…During the quiz, the user is given statements about depression, psychotherapy and psychological treatment possibilities and has to decide, if those statements are true or false. Afterwards, the user is given immediate feedback on the correctness of their answer through empathetic responses -as those have been shown to be important for the therapeutic relationship [11,21] as well as for the interaction with CAs in general [8]. Hence, feedback is adapted depending on the correctness of the user's answer and detailed information on the respective CBT-related topic is given.…”