Mining and visualising contradictory data

Abstract

Big datasets are often stored in flat files and can contain contradictory data. Contradictory data undermines the soundness of the information from a noisy dataset. Traditional tools such as pie chart and bar chart are overwhelmed when used to visually identify contradictory data in multidimensional attribute-values of a big dataset. This work explains the importance of identifying contradictions in a noisy dataset. It also examines how contradictory data in a large and noisy dataset can be mined and visually analysed. The authors developed ‘ConTra’, an open source application which applies mutual exclusion rule in identifying contradictory data, existing in comma separated values (CSV) dataset. ConTra’s capability to enable the identification of contradictory data in different sizes of datasets is examined. The results show that ConTra can process large dataset when hosted in servers with fast processors. It is also shown in this work that ConTra is 100% accurate in identifying contradictory data of objects whose attribute values do not conform to the mutual exclusion rule of a dataset in CSV format. Different approaches through which ConTra can mine and identify contradictory data are also presented.