Ontology-based Document Mining System for IT Support Service

Abstract

Information Technology (IT) is a vital and an integral part of every organization. IT executives are constantly faced with problems that are difficult to tackle and time consuming. Experience is required to solve these problems easier and faster. We can utilize case-based reasoning (CBR), data mining and information retrieval (IR) techniques to automate IT problem solving and experience management. In this paper, we propose an IT ontology-based system for semantic retrieval that increases the efficiency and quality of IT support service. The proposed approach retrieves similar problem/solution pairs based on the concepts in the query and performs better than the traditional keyword-based approach especially in cases where the keywords of the relevant documents do not match the keywords in the query.

Knowledge is Power: Provide Your IT-Support with Domain-Specific High-Quality Solution Material

“…While SUSY is still in the alpha phase the prototype proves preliminary evidence for good useability, and DF2 and DF3 already show sufficient results regarding previous studies: DF2 reached a precision of 0,87 based on 40 queries. For comparison, in [33] ten queries were evaluated with an ontology-based retrieval system for IT-Support that reached a precision of 0,86 compared to a keyword-based approach that reached a precision of 0,13. DF3 reached a recall of 0,91 to detect low-quality solution materials while in a similar study [29] crowd-support texts were analyzed and the detection of low-quality texts reached a recall of 0,75.…”