A Human Intention Detector—An Application of Sentiment Analysis

Dutta, Megha; Mondal, Shayan; Chakraborty, Sanjay; Chakraborty, Arpan

doi:10.1007/978-981-13-7403-6_57

Cited by 2 publications

(3 citation statements)

References 0 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Yet, how does the explainer's cognitive process determine the degree and type of generalization required? While such a determination is itself a very difficult open research question being pursued by numerous researchers in fields such as culture modelling [53,54], user modelling [55][56][57], emotion recognition [58][59][60][61][62][63][64][65][66], and human computer interaction [67][68][69][70][71][72], we are interested in how the determination, once made, can be used to affect the explanation provided. We propose that this question implies that the cognitive and social processes form a cycle, as shown in Figure 2.…”

Section: Learning Processmentioning

confidence: 99%

“…This modeling of external actors is an active research field with substantial work already caried out. For instance, culture modelling [53,54], user modelling [55][56][57], emotion recognition [58][59][60][61][62][63][64][65][66], action recognition [136][137][138][139][140][141][142], pedestrian prediction [143][144][145][146][147][148] and human intention modelling [69][70][71][72] are just a few areas that could be considered as modelling external actors.…”

Section: Agentmentioning

confidence: 99%

“…This stage illustrates a relationship with Second-order intentionality, where the agent's choice of behaviour, the explanation, is determined by a model of the explainee. User modelling in Human Computer Interaction (HCI) [67][68][69][70][71][72] approaches can be used to model the explainee allowing more meaningful interpretations of the questions. This is evident in recent work in the emerging field of Personalised Explanations [231].…”

Section: Levels Of Xaimentioning

confidence: 99%

See 2 more Smart Citations

Levels of explainable artificial intelligence for human-aligned conversational explanations

Dazeley

Vamplew

Foale

et al. 2021

Artificial Intelligence

View full text Add to dashboard Cite

Over the last few years there has been rapid research growth into eXplainable Artificial Intelligence (XAI) and the closely aligned Interpretable Machine Learning (IML). Drivers for this growth include recent legislative changes and increased investments by industry and governments, along with increased concern from the general public. People are affected by autonomous decisions every day and the public need to understand the decision-making process to accept the outcomes. However, the vast majority of the applications of XAI/IML are focused on providing low-level 'narrow' explanations of how an individual decision was reached based on a particular datum. While important, these explanations rarely provide insights into an agent's: beliefs and motivations; hypotheses of other (human, animal or AI) agents' intentions; interpretation of external cultural expectations; or, processes used to generate its own explanation. Yet all of these factors, we propose, are essential to providing the explanatory depth that people require to accept and trust the AI's decision-making. This paper aims to define levels of explanation and describe how they can be integrated to create a human-aligned conversational explanation system. In so doing, this paper will survey current approaches and discuss the integration of different technologies to achieve these levels with Broad eXplainable Artificial Intelligence (Broad-XAI), and thereby move towards high-level 'strong' explanations.

show abstract