Automated judgment of document qualities

Abstract

The authors report on a series of experiments to automate the assessment of document qualities such as depth and objectivity. The primary purpose is to develop a qualitysensitive functionality, orthogonal to relevance, to select documents for an interactive question-answering system. The study consisted of two stages. In the classifier construction stage, nine document qualities deemed important by information professionals were identified and classifiers were developed to predict their values. In the confirmative evaluation stage, the performance of the developed methods was checked using a different document collection. The quality prediction methods worked well in the second stage. The results strongly suggest that the best way to predict document qualities automatically is to construct classifiers on a person-by-person basis.

Daten- und Informationsqualität

“…Untersuchungen, die anhand von Nachrichtenartikeln durchgeführt wurden, verweisen auf zwei Aspekte (Ng et al 2006;Tang et al 2003): Zum einen dominieren bei der Wahrnehmung der Qualität eines Dokumentes individuelle Unterschiede stark, andererseits bieten die durch eine Textanalyse erhaltenen Dokumenteigenschaften ausreichend Informationen für einen Klassifikator, um insbesondere Qualitätseigenschaften zu prognostizieren, solange die Klassifikation der Dokumente konsistent durchgeführt wird (z. B. durch den gleichen Beurteiler).…”

The Value of Software Documentation Quality

“…The third question examines which quality attributes are seen as important for software documentation. Therefore, we asked the respondents to rate several software documentation-related quality attributes derived from different documentation standards, guidelines and scientific work (e.g., [17], [18], [19], and [20]). Moreover, we gave for each quality attribute a short description.…”