Explainable AI (XAI): A Systematic Meta-Survey of Current Challenges and Future Opportunities

The past decade has seen significant progress in artificial intelligence\n(AI), which has resulted in algorithms being adopted for resolving a variety of\nproblems. However, this success has been met by increasing model complexity and\nemploying black-box AI models that lack transparency. In response to this need,\nExplainable AI (XAI) has been proposed to make AI more transparent and thus\nadvance the adoption of AI in critical domains. Although there are several\nreviews of XAI topics in the literature that identified challenges and\npotential research directions in XAI, these challenges and research directions\nare scattered. This study, hence, presents a systematic meta-survey for\nchallenges and future research directions in XAI organized in two themes: (1)\ngeneral challenges and research directions in XAI and (2) challenges and\nresearch directions in XAI based on machine learning life cycle's phases:\ndesign, development, and deployment. We believe that our meta-survey\ncontributes to XAI literature by providing a guide for future exploration in\nthe XAI area.\n