Using Gunnnig-Fog Index to Assess Instant Messages Readability from ECAs

Abstract

In this paper, we examine the readability of the human-machine conversation transcripts in the instant messaging environment based on the Gunning-fog index. The study is based on an embodied conversational agent (ECA) called artificial intelligent natural-language identity (AINI) which was designed to mimic human conversation. The ECA is also expected to supply answers with a sense of humour. We report on the collection and analysis of a corpus containing over 3,280 utterances in a series of real instant messages exchanged between AINI with 65 online "buddies".