Linguistic Differences in Real Conversations: Human to Human vs Human to Chatbot
Sammanfattning: This study investigates how students communicate in writing when they know thattheir conversational partner is a human being in comparison to how they communicate whenthey know their partner is a chatbot. The participants are upper secondary students of English.The investigation took place in a school in Sweden where English is taught as a foreignlanguage. The students wrote to their peers through Instant Messaging (IM) and to the chatbot‘Mitsuku’ through the website of ‘pandorabots’. The conversations were compared, and theirlinguistic variables were distinguished according to the following dimensions: words permessage and per conversation, messages per conversation, lexical diversity, frequency ofprofanity and use of abbreviations, acronyms and emoticons. During the last few years, bothlinguists and AI researchers have been compelled to deal with problems of context, syntax,semantics and pragmatics (Rosenberg, 1975). There are studies that address the issue ofcooperation between linguistics and natural language processing (NLP) that focus on howchatbots communicate in writing with humans. However, this study is focused on humans,evaluating the language and distinguishing the linguistic characteristics used from the side ofpeople conversing with a chatbot. The results showed that student-chatbot messages containedfewer words per message than those sent to another student, but students sent more than twiceas many messages to the chatbot than to their peers. The study revealed that there is a higherlevel of motivation in students when they engage in conversations with the artificial agent vsother students.
HÄR KAN DU HÄMTA UPPSATSEN I FULLTEXT. (följ länken till nästa sida)