Please use this identifier to cite or link to this item: https://www.um.edu.mt/library/oar/handle/123456789/92845
Title: CSAIBot : the BOSIT conversational agent
Authors: Aquilina, Maria E. (2004)
Keywords: Intelligent agents (Computer software)
Natural language generation (Computer science)
Artificial intelligence
XML (Document markup language)
Issue Date: 2004
Citation: Aquilina, M. E. (2004). CSAIBot : the BOSIT conversational agent (Bachelor’s dissertation).
Abstract: A conversational agent is a software conversational simulator which gives the appearance of maintaining a conversation with a person in natural language. This usually happens within a typed textual environment, having the software agent program residing either on a local machine or, as is usually the case, on a remote server accessible via the Internet. Conversational agents, or chatterbots, usually do not attempt to get a good understanding of an ongoing conversation. Instead they attempt to pick up cue words or phrases from the person, which would allow them to use pre-calculated responses to their advantage. These responses create the impression that the agents are conducting the conversation in an apparently meaningful way without requiring them to know what they are actually talking about. Chatbots serve a multitude of functions, these varying from simply acting as a listening companion to more complex personal agent-forms catering for specific user needs. CSAIBot falls in the latter category. CSAIBot is a conversational agent aimed to act as a personal assistant for both departmental staff and students posing queries related to the B.Sc.(Hons.)I.T. course. This interaction would mostly follow a free question-answering method, enabling the user to glean specific information about the course depending only on the question asked. User requests can also trigger task dialogues in which a fixed pattern of interaction must be followed, such as in the case of setting up an appointment directly with a staff member. CSAIBot makes use of surface-oriented techniques combined with a superficial analysis of the user's input in order to try and achieve responses which go beyond the capabilities of typical chatbots.
Description: B.Sc. IT (Hons)(Melit.)
URI: https://www.um.edu.mt/library/oar/handle/123456789/92845
Appears in Collections:Dissertations - FacICT - 1999-2009
Dissertations - FacICTCS - 1999-2007

Files in This Item:
File Description SizeFormat 
BSC(HONS)IT_Aquilina_Maria E._2004.PDF
  Restricted Access
22.98 MBAdobe PDFView/Open Request a copy


Items in OAR@UM are protected by copyright, with all rights reserved, unless otherwise indicated.