The Role of Automated Categorisation in e-Government Information Retrieval

High-precision search results are essential for supporting e-government employees’ information tasks. Prior studies have shown that existing features of e-government retrieval systems need improvement in terms of search facilities, navigation and metadata. This paper investigates how automated categorisation can enhance information organisation and retrieval and presents the results of a realistic evaluation that compared automated categorisation and free text indexing of the government intranet used by Danish tax authorities. Thirty-two individuals participated in the evaluation, which conducted a combination of simulated searches and genuine search tasks. Searching behaviour and search outcome was documented by search logs, relevance assessments, and post search interviews. The evaluation demonstrates a high potential for automated categorisation in a government context. Overall, the categorised organisation generated more reformulations at session level and less success at query level. Session success was found to be fairly even between the two systems. Categorised overviews were useful if the participant did not possess much knowledge of the task at hand. When task knowledge was present, categorisation was used to support the assumptions of a correct search. Participants avoided automated categorisation if high-precision documents were among the top results or if few documents were retrieved. The findings emphasise the importance of simultaneously providing different search options for e-government IR systems, and they reveal that automated categorisation is a valuable candidate for improving search facilities within this domain.