Conversations with AI : discussing ethics in NLP

Abstract

Artificial Intelligence (AI) has already begun to transform our daily lives, and its impact will only grow in the coming years. As AI becomes more prevalent, it is crucial to address the ethical considerations that come with its implementation. It is essential to educate young people on AI ethics so that they are prepared for the ethical challenges that will arise. Chatbots or conversational agents (CA) are software applications that engage in conversations with a single user either by voice or text. Their main objective is to identify and provide the best response for any request the user issues. The best response should effectively address the question and include relevant information while following grammatical and lexical rules. This research proposes the development of a CA with the capability of addressing young people about ethics in NLP. The benefits of this project are numerous, including increasing awareness of AI ethics among young people, improving engagement with the subject matter, and promoting ethical decision-making skills. The methodology for developing the CA uses NLP and machine learning to understand user input and generate responses based on predefined patterns and tags. Machine learning is a category of AI methods that empower machines without being directly programmed, implying that the software changes itself when exposed to new input. To achieve accurate recognition of user intent, the system incorporates various machine learning algorithms such as Decision Tree Classifier, Naïve Bayes Method, Support Vector Machine, and Deep Neural Networks. These algorithms analyze the input to identify the intended purpose of the user’s message. Based on the recognized intents and extracted entities, the system generates responses using a knowledge base containing predefined answers. To enhance user experience and facilitate interactive engagement, a user-friendly graphical user interface (GUI) is integrated into the chatbot. This GUI allows users to easily interact with the system and participate in discussions about ethical considerations in NLP. The evaluation of the chatbot’s efficacy encompassed a comprehensive assessment of both its technical performance and user feedback. Technical performance evaluation involved comparing different methods for accurately interpreting and responding to user inputs. User evaluation was conducted through surveys and interactions with the chatbot, providing valuable insights into educational impact and user experience. Surveys were utilized to gauge user knowledge before and after engaging with the chatbot. The evaluation results indicated that the chatbot successfully educated young individuals about ethical considerations in NLP and fostered meaningful discussions on the subject. This project can help ensure that young people are prepared to make informed decisions as AI continues to grow and shape our world. Additionally, the CA developed within this project can be readily customized and integrated into existing educational platforms, making it accessible to a broader audience.