|
| # | Study | Purpose |
|
| 1 | [78] | 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 |
| 12 | [49] | To develop a topic-aware emotional response generation (TERG) model, which can not only exactly generate desired emotional response but also perform well in topic relevance |
| 13 | [56] | To embed emotion and topic in the input data to generate meaningful and emotionally relevant responses |
| 14 | [66] | To develop and evaluate a multiresolution adversarial model that generates more empathetic responses |
| 15 | [50] | To elicit a topic-coherent response embedded with emotion using a loss function to predict the corresponding word in every generation step |
| 16 | [67] | To develop an online empathetic chatbot influenced by emotion information using large-scale empathetic conversational datasets to detect the user’s emotion or ask questions for self-disclosure |
| 17 | [68] | To develop a model that selects an appropriate reaction by learning the context and underlying emotion |
| 18 | [36] | Used an affective lexicon to embed sentiments into the word vectors and used a CVAE-based dialog model to generate diverse and emotional responses |
| 19 | [62] | To develop an AI-driven chat-oriented dialog system that dynamically imitates human emotions in the conversation |
| 20 | [63] | To elicit a more positive emotional valence throughout a chat-based interaction in order to promote positive emotional states |
| 21 | [72] | To develop three weakly supervised models that can generate diverse, polite (or rude) dialog responses using data from separate style and dialog domains |
| 22 | [51] | To propose a generative model that fuses word- and sentence-level emotions to model the dialog text and learn emotional expression in order to control the emotional feature of the generated response |
| 23 | [57] | To present a topic-enhanced emotional conversation generation model that incorporates emotional factors and topic information into the conversation system |
| 24 | [17] | To use a custom-built empathetic conversational dataset and explore different ways of combining information from related tasks that can lead to more empathetic responses |
| 25 | [76] | To generate meaningful responses embedded with explicit or implicit emotion |
| 26 | [54] | To develop a new approach of context-relevant emotional responses using the bidirectional Seq2Seq model |
| 27 | [7] | To create an emotionally intelligent chatbot using emotional tags on the posts and recognize the emotional dimension |
| 28 | [55] | To use reinforcement learning with emotional editing constraints to generate more meaningful and customizable emotional responses |
| 29 | [79] | To create a bilingual-aided interactive approach that can simultaneously and interactively generate bilingual emotional replies to monolingual posts |
| 30 | [80] | To provide social support for community members in an online health community using a Seq2Seq model-based chatbot that recognizes emotion and produces diverse responses |
| 31 | [59] | To build a unified neural architecture in order to encode the semantics and affect for generating more intelligent responses with expressed emotions |
| 32 | [58] | To extract the emotional and semantic information of the interlocutor to generate logical responses embedded with emotion |
| 33 | [83] | To develop an anthropomorphic model and present its ability to understand the human interlocutor using both the subjective and objective measures |
| 34 | [84] | To create an empathetic conversation system that incorporates emotional factors added to semantics and to enhance the context-response through a multitask learning framework |
| 35 | [52] | To design an artificial conversational chatting machine that generates nondeterministic responses providing the same input with different emotional contexts that are empathetically coherent |
| 36 | [73] | To propose a multiemotional conversation system (MECS) and evaluate the model at both the context level and the emotion level |
| 37 | [53] | To develop a dual-factor generation model that fits the conversation data and actively controls the generation of the response with respect to sentiment or topic specificity |
| 38 | [65] | To develop an intelligent open-domain neural conversational model that produces responses that are syntactically and semantically appropriate and rich in emotion |
| 39 | [74] | To propose a neural conversation generation with auxiliary emotional supervised models where the dialog generation system is characterized by emotional intelligence |
| 40 | [61] | To propose a model to generate emotional responses using internal and external memory |
| 41 | [48] | To present the design and implementation of XiaoIce, a multimodal chatbot that recognizes and responds with emotion in an open-domain conversation |
| 42 | [75] | To apply emotion detection with emojis using a reinforced CVAE model to generate affective responses that contain emojis |
|
