Robert-Jan Sips

Utilizing Data Mining for Predictive Modeling of Colorectal Cancer Using Electronic Medical Records

Colorectal cancer (CRC) is a relatively common cause of death around the globe. Predictive models for the development of CRC could be highly valuable and could facilitate an early diagnosis and increased survival rates. Currently available predictive models are improving, but do not fully utilize the wealth of data available about patients in routine care nor do they take advantage of the developments in the area of data mining. In this paper, a first attempt to generate a predictive model using the CHAID decision tree learner based on anonymously extracted Electronic Medical Records is reported, showing an area under the curve (AUC) of .839 for the adult population and .702 for the age group between 55 and 75.

A study of the online profile of enterprise users in professional social networks

Understanding the impact of corporate information publicly distributed on the Web is becoming more and more crucial. In this paper we report the result of a study that involved 130 IBM employees: we explored the correctness and extent of organisational information that can be observed from the online profiles of a companys employees. Our work contributes new insights to the study of social networks by showing that, even by considering a small fraction of the available online data, it is possible to discover accurate information about an organisation, its structure, and the factors that characterise the social reach of their employees.

Online social network evolution: Revisiting the Twitter graph

In 2010 the popular paper by Kwak et al. [11] presented the first comprehensive study of Twitter as it appeared in 2009, using most of the Twitter network at the time. Since then, Twitters popularity and usage has exploded, experiencing a 10-fold increase. As of 2015, it has more than 500 million users, out of which 316 million are active, i.e. logging into the service at least once a month.1 In this study we revisit the network observed by Kwak et al. to examine the changes exhibited in both the graph and the behavior of the users in it. Our results conclude to a denser network, showing an increase in the number of reciprocal edges, despite the fact that around 12.5% of the 2009 users have now left Twitter. However, the networks largest strongly connected component seems to be significantly decreasing, suggesting a movement of edges towards popular users. Furthermore, we observe numerous changes in the lists of influential Twitter users, having several accounts that where not popular in the past securing a position in the top-20 list as new entries.