Web Data Mining for Public Health Purposes

Research output: Book/ReportPh.D. thesis

Standard

Web Data Mining for Public Health Purposes. / Hansen, Niels Dalum.

Department of Computer Science, Faculty of Science, University of Copenhagen, 2017.

Research output: Book/ReportPh.D. thesis

Harvard

Hansen, ND 2017, Web Data Mining for Public Health Purposes. Department of Computer Science, Faculty of Science, University of Copenhagen. <https://soeg.kb.dk/permalink/45KBDK_KGL/1pioq0f/alma99122355264805763>

APA

Hansen, N. D. (2017). Web Data Mining for Public Health Purposes. Department of Computer Science, Faculty of Science, University of Copenhagen. https://soeg.kb.dk/permalink/45KBDK_KGL/1pioq0f/alma99122355264805763

Vancouver

Hansen ND. Web Data Mining for Public Health Purposes. Department of Computer Science, Faculty of Science, University of Copenhagen, 2017.

Author

Hansen, Niels Dalum. / Web Data Mining for Public Health Purposes. Department of Computer Science, Faculty of Science, University of Copenhagen, 2017.

Bibtex

@phdthesis{a77463babf794bc0ac315bd5fcf9eb41,
title = "Web Data Mining for Public Health Purposes",
abstract = "For a long time, public health events, such as disease incidence or vaccination activity, havebeen monitored to keep track of the health status of the population, allowing to evaluatethe effect of public health initiatives and to decide where resources for improving publichealth are best spent. This thesis investigates the use of web data mining for public healthmonitoring, and makes contributions in the following two areas:(I) New approaches for predicting public health events from web mined data. Theseinclude: (i) An online learning method that can automatically adapt to sudden temporalchanges in the underlying signal. Health events often show temporal stability through manyyears and historical data is therefore often a good predictor, but in the case of suddenchanges, this assumption no longer holds. Our online learning method aims at addressing thisproblem by automatically adjusting to temporal changes. (ii) Prediction models factoringevent seasonality. We show how the expected seasonal variation can be used to optimize theusage of web mined data. (iii) Novel web data mining strategies that make it possible totarget different population groups and reduce spurious correlations.(II) Novel applications of web mined data. These cover: (i) Prediction using web mineddata of health events, such as preventive measures and drug consumption. Prior research hasprimarily focused on prediction of contagious diseases, but public health institutions are alsoresponsible for monitoring several other types of health events. Our extensions to preventivemeasures and drug consumption show that the potential of web mined data is far from fullyutilized. (ii) Understanding the relationship between news media and vaccination uptake.With the constant availability of news, both online and in print, understanding the effect ofnews media on public health events is important for designing accurate health monitoringsystems. Increased understanding can, in addition, be useful in a variety of public healthtasks, e.g. designing outreach campaigns.",
author = "Hansen, {Niels Dalum}",
year = "2017",
language = "English",
publisher = "Department of Computer Science, Faculty of Science, University of Copenhagen",

}

RIS

TY - BOOK

T1 - Web Data Mining for Public Health Purposes

AU - Hansen, Niels Dalum

PY - 2017

Y1 - 2017

N2 - For a long time, public health events, such as disease incidence or vaccination activity, havebeen monitored to keep track of the health status of the population, allowing to evaluatethe effect of public health initiatives and to decide where resources for improving publichealth are best spent. This thesis investigates the use of web data mining for public healthmonitoring, and makes contributions in the following two areas:(I) New approaches for predicting public health events from web mined data. Theseinclude: (i) An online learning method that can automatically adapt to sudden temporalchanges in the underlying signal. Health events often show temporal stability through manyyears and historical data is therefore often a good predictor, but in the case of suddenchanges, this assumption no longer holds. Our online learning method aims at addressing thisproblem by automatically adjusting to temporal changes. (ii) Prediction models factoringevent seasonality. We show how the expected seasonal variation can be used to optimize theusage of web mined data. (iii) Novel web data mining strategies that make it possible totarget different population groups and reduce spurious correlations.(II) Novel applications of web mined data. These cover: (i) Prediction using web mineddata of health events, such as preventive measures and drug consumption. Prior research hasprimarily focused on prediction of contagious diseases, but public health institutions are alsoresponsible for monitoring several other types of health events. Our extensions to preventivemeasures and drug consumption show that the potential of web mined data is far from fullyutilized. (ii) Understanding the relationship between news media and vaccination uptake.With the constant availability of news, both online and in print, understanding the effect ofnews media on public health events is important for designing accurate health monitoringsystems. Increased understanding can, in addition, be useful in a variety of public healthtasks, e.g. designing outreach campaigns.

AB - For a long time, public health events, such as disease incidence or vaccination activity, havebeen monitored to keep track of the health status of the population, allowing to evaluatethe effect of public health initiatives and to decide where resources for improving publichealth are best spent. This thesis investigates the use of web data mining for public healthmonitoring, and makes contributions in the following two areas:(I) New approaches for predicting public health events from web mined data. Theseinclude: (i) An online learning method that can automatically adapt to sudden temporalchanges in the underlying signal. Health events often show temporal stability through manyyears and historical data is therefore often a good predictor, but in the case of suddenchanges, this assumption no longer holds. Our online learning method aims at addressing thisproblem by automatically adjusting to temporal changes. (ii) Prediction models factoringevent seasonality. We show how the expected seasonal variation can be used to optimize theusage of web mined data. (iii) Novel web data mining strategies that make it possible totarget different population groups and reduce spurious correlations.(II) Novel applications of web mined data. These cover: (i) Prediction using web mineddata of health events, such as preventive measures and drug consumption. Prior research hasprimarily focused on prediction of contagious diseases, but public health institutions are alsoresponsible for monitoring several other types of health events. Our extensions to preventivemeasures and drug consumption show that the potential of web mined data is far from fullyutilized. (ii) Understanding the relationship between news media and vaccination uptake.With the constant availability of news, both online and in print, understanding the effect ofnews media on public health events is important for designing accurate health monitoringsystems. Increased understanding can, in addition, be useful in a variety of public healthtasks, e.g. designing outreach campaigns.

UR - https://soeg.kb.dk/permalink/45KBDK_KGL/1pioq0f/alma99122355264805763

M3 - Ph.D. thesis

BT - Web Data Mining for Public Health Purposes

PB - Department of Computer Science, Faculty of Science, University of Copenhagen

ER -

ID: 200969936