Vanja Ljevar, PhD | University of Nottingham (original) (raw)
Papers by Vanja Ljevar, PhD
2021 IEEE International Conference on Big Data (Big Data), Dec 15, 2021
Asthma affects an estimated 300 million people across the world. Despite being a highly treatable... more Asthma affects an estimated 300 million people across the world. Despite being a highly treatable condition using preventative inhalers, mortality rates remain unacceptably high, with lack of adherence to medications cited as a major cause. While various drivers for non-adherence have been considered in isolation, interactions between demographic, behavioural and situational factors have never been modelled in concert mostly due to the limited ability of traditional methods to group such a large variety of features. This was addressed in this paper through a non-linear modelling approach, leveraging a novel dataset obtained via online surveying of asthma patients. Application of traditional variable importance methods to examine explanatory factors, however, is not possible. This is due to the presence of high multicollinearity in the data, a highly common occurrence in big data, or any datasets which include a large number of input features. This results in insights being obfuscated by extensive shared information and non-linear interactions occurring across variables. To mitigate this, we introduce the first Grouped Feature approach to Model Class Reliance (Group-MCR), that is able to quantify the importance of specific variable sets in underpinning explanations. Cross-validated models achieve 71% accuracy, with Group-MCR revealing the importance of perceptual factors. Out of all the perceptual factors denial proves to be most predictive of non-adherence to asthma medication, indicating that public health interventions should not only target the physical aspects of asthma, but additionally focus on patients’ beliefs and perceptions as valuable parts of their treatment.
The links between anxiety (and negative mental heath outcomes in general) and socio-economic cond... more The links between anxiety (and negative mental heath outcomes in general) and socio-economic conditions have been the subject of a large number of studies. However, the underlying mechanisms that affect this relationship have not been fully elucidated, nor have they been extended to consider potential mediators in the form of individual differences/psychological traits. Interrogating over 8-million customers’ loyalty card transactions from a major health retailer, this paper investigated two ideas: the potential to use health product purchases to detect anxiety distributions across geo-spatial regions in England; and exploring the relationship between these product health purchases, deprivation levels and personality traits. Specifically, this analysis examined the co-variation between: anxiety purchases within district level geo-spatial regions in the UK; mean deprivation levels; and personality traits, across those districts. Contrary to previous findings, results demonstrated a negative correlation between anxiety related purchases and deprivation, and a positive correlation between anxiety related purchases and conscientiousness. This indicated the complex nature of the various forms of anxiety and its underlying causes and drivers - but also highlighted the challenges faced by different demographics in treating its symptoms.
Both models propose that health threat or symptoms result in cognitive or emotional representatio... more Both models propose that health threat or symptoms result in cognitive or emotional representation of a health condition (Broadbent et al., 2006). HBM posits that patients' willingness to adhere to a preventative behaviour depends on factors such as perceived benefits of preventative strategies, perceived severity, cues to action or self-efficacy (Champion, Skinner, et al., 2008; Naimi et al., 2009). The SR model recognises that apart from cognitive processes, emotional processes take place independently (Harvey & Lawson, 2009). Therefore, SR accounts for both emotional and rational responses to health threats and focuses on the representation of illness, behaviours that are adopted in order to adjust to these perceptions and the efficacy of these behaviours (Broadbent et al., 2006; Harvey & Lawson, 2009). However, these models do not include perceptions that exist outside of patients' control, such as perceptions of other people, which may also affect patients' behaviours. Based on HBM and SR models, several studies examined patients' perceptions. For example, Lehane et al. (2018) examined the acceptance of the mental health condition that was inversely associated with the psychological distress (Lehane, Nielsen, Wittich, Langer, & Dammeyer, 2018). In relation to asthma, work was done regarding the perceptions about the length of a condition; patients' descriptions of asthma and symptoms that had impact on adherence (Leventhal, Nerenz, & Steele, 2020);and perceptions about asthma control that identified barriers and drivers to self-management (Bidad, Barnes, Griffiths, & Horne, 2018). Patients who perceived few negative consequences of taking their medication had bet
Patients’ perceptions about their condition have a strong impact on not only adherence to medicat... more Patients’ perceptions about their condition have a strong impact on not only adherence to medication, but also on how they view themselves in the light of their condition. Research implies that Twitter is a particularly rich source of perceptions, as patients frequently use internet for information sharing and support. However, Twitter contains a lot of noise in the form of tweets that do not relate to perceptions, but are rather generated to advertise research and corporate news and this kind of information could ‘pollute’ perception analysis. This study examined methods that could be used to extract perception tweets, on the example of tweets related to asthma. We first demonstrated differences between perception and non-perception tweets in terms of their linguistic features, and then focused on filtering perceptions using the classification process. Results demonstrated that there is a significant difference between perceptions and non-perceptions: perception tweets are shorter, have less capital letters, less punctuation signs and less hashtags. These features also performed well in predicting perceptions. However, the bag of words approach had better results in distinguishing between perception and non-perception tweets and the best results were obtained using word-based frequency vectorization and by training a neural network based classifier. Future research could explore the synergy of these approaches.
Frontiers in Psychology, Jun 15, 2021
International Journal of Population Data Science
Introduction & BackgroundIt has been reported that up to 91% of those who menstruate experience a... more Introduction & BackgroundIt has been reported that up to 91% of those who menstruate experience associated pain. Despite its ubiquity, the prevalence of menstrual pain has been under researched due to stigma, disregard from medical professionals and a lack of data. It has also been reported that different demographics experience menstrual pain differently yet the impact of socio-demographic factors on menstrual pain remains to be explored on a national scale due to data scarcity. Objectives & ApproachIn this study, we propose one way to overcome this data barrier, using a novel measure of menstrual pain extracted from supermarket shopping data. We use these national datasets to identify individual customer behaviour patterns. Specifically, we use transactions involving both a pain and menstrual item as a proxy measure for menstrual pain. We investigate national menstrual pain sales and whether there are significant differences between deprived and less deprived areas of England. Rel...
2022 IEEE International Conference on Big Data (Big Data), Dec 17, 2022
Objectives. There are, on average, three people who die daily from an asthma attack in the UK. As... more Objectives. There are, on average, three people who die daily from an asthma attack in the UK. Asthma self-management and good adherence can reduce this rate of mortality. Since adherence to preventative medication is important for many people with asthma, we investigated asthma patients' and non-patients’ perceptions about asthma, the similarities between themes in interviews and on Twitter and potential influence on adherence. Design. Both patients' and non-patients' perceptions about asthma were examined in a combination of interviews and content analysis of Twitter data.Methods. Fourteen semi-structured interviews were conducted and analysed using thematic analysis; A coding instrument was developed to capture perceptions on Twitter and a content analysis was conducted on 3.000 tweets. Convergence analysis identified similar topics between interviews and social media data analysis and where these were similar or different. Results. Several themes emerged from intervi...
2021 IEEE International Conference on Big Data (Big Data)
2020 IEEE International Conference on Big Data (Big Data), 2020
The links between anxiety (and negative mental heath outcomes in general) and socio-economic cond... more The links between anxiety (and negative mental heath outcomes in general) and socio-economic conditions have been the subject of a large number of studies. However, the underlying mechanisms that affect this relationship have not been fully elucidated, nor have they been extended to consider potential mediators in the form of individual differences/psychological traits. Interrogating over 8-million customers’ loyalty card transactions from a major health retailer, this paper investigated two ideas: the potential to use health product purchases to detect anxiety distributions across geo-spatial regions in England; and exploring the relationship between these product health purchases, deprivation levels and personality traits. Specifically, this analysis examined the co-variation between: anxiety purchases within district level geo-spatial regions in the UK; mean deprivation levels; and personality traits, across those districts. Contrary to previous findings, results demonstrated a n...
Frontiers in Psychology
Behavioural scientists have been studying public perceptions to understand how and why people beh... more Behavioural scientists have been studying public perceptions to understand how and why people behave the way they do towards climate change. In recent times, enormous changes to behaviour and people’s interactions have been brought about by the worldwide coronavirus disease 2019 (COVID-19) pandemic, unexpectedly and indefinitely; some of which have environmental implications (e.g., travelling less). An innovative way to analyse public perceptions and behaviour is with the use of social media to understand the discourse around climate change. This paper focuses on assessing changes in social media discourse around actions for climate change mitigation over time during the global pandemic. Twitter data were collected at three different points during the pandemic: February (time 1), June (time 2), and October 2020 (time 3). By using machine learning techniques, including recurrent neural networks (RNN) and unsupervised learning Latent Dirichlet Allocation (LDA) topic modelling, we iden...
2020 IEEE International Conference on Big Data (Big Data), 2020
Patients’ perceptions about their condition have a strong impact on not only adherence to medicat... more Patients’ perceptions about their condition have a strong impact on not only adherence to medication, but also on how they view themselves in the light of their condition. Research implies that Twitter is a particularly rich source of perceptions, as patients frequently use internet for information sharing and support. However, Twitter contains a lot of noise in the form of tweets that do not relate to perceptions, but are rather generated to advertise research and corporate news and this kind of information could ‘pollute’ perception analysis. This study examined methods that could be used to extract perception tweets, on the example of tweets related to asthma. We first demonstrated differences between perception and non-perception tweets in terms of their linguistic features, and then focused on filtering perceptions using the classification process. Results demonstrated that there is a significant difference between perceptions and non-perceptions: perception tweets are shorter,...
2021 IEEE International Conference on Big Data (Big Data), Dec 15, 2021
Asthma affects an estimated 300 million people across the world. Despite being a highly treatable... more Asthma affects an estimated 300 million people across the world. Despite being a highly treatable condition using preventative inhalers, mortality rates remain unacceptably high, with lack of adherence to medications cited as a major cause. While various drivers for non-adherence have been considered in isolation, interactions between demographic, behavioural and situational factors have never been modelled in concert mostly due to the limited ability of traditional methods to group such a large variety of features. This was addressed in this paper through a non-linear modelling approach, leveraging a novel dataset obtained via online surveying of asthma patients. Application of traditional variable importance methods to examine explanatory factors, however, is not possible. This is due to the presence of high multicollinearity in the data, a highly common occurrence in big data, or any datasets which include a large number of input features. This results in insights being obfuscated by extensive shared information and non-linear interactions occurring across variables. To mitigate this, we introduce the first Grouped Feature approach to Model Class Reliance (Group-MCR), that is able to quantify the importance of specific variable sets in underpinning explanations. Cross-validated models achieve 71% accuracy, with Group-MCR revealing the importance of perceptual factors. Out of all the perceptual factors denial proves to be most predictive of non-adherence to asthma medication, indicating that public health interventions should not only target the physical aspects of asthma, but additionally focus on patients’ beliefs and perceptions as valuable parts of their treatment.
The links between anxiety (and negative mental heath outcomes in general) and socio-economic cond... more The links between anxiety (and negative mental heath outcomes in general) and socio-economic conditions have been the subject of a large number of studies. However, the underlying mechanisms that affect this relationship have not been fully elucidated, nor have they been extended to consider potential mediators in the form of individual differences/psychological traits. Interrogating over 8-million customers’ loyalty card transactions from a major health retailer, this paper investigated two ideas: the potential to use health product purchases to detect anxiety distributions across geo-spatial regions in England; and exploring the relationship between these product health purchases, deprivation levels and personality traits. Specifically, this analysis examined the co-variation between: anxiety purchases within district level geo-spatial regions in the UK; mean deprivation levels; and personality traits, across those districts. Contrary to previous findings, results demonstrated a negative correlation between anxiety related purchases and deprivation, and a positive correlation between anxiety related purchases and conscientiousness. This indicated the complex nature of the various forms of anxiety and its underlying causes and drivers - but also highlighted the challenges faced by different demographics in treating its symptoms.
Both models propose that health threat or symptoms result in cognitive or emotional representatio... more Both models propose that health threat or symptoms result in cognitive or emotional representation of a health condition (Broadbent et al., 2006). HBM posits that patients' willingness to adhere to a preventative behaviour depends on factors such as perceived benefits of preventative strategies, perceived severity, cues to action or self-efficacy (Champion, Skinner, et al., 2008; Naimi et al., 2009). The SR model recognises that apart from cognitive processes, emotional processes take place independently (Harvey & Lawson, 2009). Therefore, SR accounts for both emotional and rational responses to health threats and focuses on the representation of illness, behaviours that are adopted in order to adjust to these perceptions and the efficacy of these behaviours (Broadbent et al., 2006; Harvey & Lawson, 2009). However, these models do not include perceptions that exist outside of patients' control, such as perceptions of other people, which may also affect patients' behaviours. Based on HBM and SR models, several studies examined patients' perceptions. For example, Lehane et al. (2018) examined the acceptance of the mental health condition that was inversely associated with the psychological distress (Lehane, Nielsen, Wittich, Langer, & Dammeyer, 2018). In relation to asthma, work was done regarding the perceptions about the length of a condition; patients' descriptions of asthma and symptoms that had impact on adherence (Leventhal, Nerenz, & Steele, 2020);and perceptions about asthma control that identified barriers and drivers to self-management (Bidad, Barnes, Griffiths, & Horne, 2018). Patients who perceived few negative consequences of taking their medication had bet
Patients’ perceptions about their condition have a strong impact on not only adherence to medicat... more Patients’ perceptions about their condition have a strong impact on not only adherence to medication, but also on how they view themselves in the light of their condition. Research implies that Twitter is a particularly rich source of perceptions, as patients frequently use internet for information sharing and support. However, Twitter contains a lot of noise in the form of tweets that do not relate to perceptions, but are rather generated to advertise research and corporate news and this kind of information could ‘pollute’ perception analysis. This study examined methods that could be used to extract perception tweets, on the example of tweets related to asthma. We first demonstrated differences between perception and non-perception tweets in terms of their linguistic features, and then focused on filtering perceptions using the classification process. Results demonstrated that there is a significant difference between perceptions and non-perceptions: perception tweets are shorter, have less capital letters, less punctuation signs and less hashtags. These features also performed well in predicting perceptions. However, the bag of words approach had better results in distinguishing between perception and non-perception tweets and the best results were obtained using word-based frequency vectorization and by training a neural network based classifier. Future research could explore the synergy of these approaches.
Frontiers in Psychology, Jun 15, 2021
International Journal of Population Data Science
Introduction & BackgroundIt has been reported that up to 91% of those who menstruate experience a... more Introduction & BackgroundIt has been reported that up to 91% of those who menstruate experience associated pain. Despite its ubiquity, the prevalence of menstrual pain has been under researched due to stigma, disregard from medical professionals and a lack of data. It has also been reported that different demographics experience menstrual pain differently yet the impact of socio-demographic factors on menstrual pain remains to be explored on a national scale due to data scarcity. Objectives & ApproachIn this study, we propose one way to overcome this data barrier, using a novel measure of menstrual pain extracted from supermarket shopping data. We use these national datasets to identify individual customer behaviour patterns. Specifically, we use transactions involving both a pain and menstrual item as a proxy measure for menstrual pain. We investigate national menstrual pain sales and whether there are significant differences between deprived and less deprived areas of England. Rel...
2022 IEEE International Conference on Big Data (Big Data), Dec 17, 2022
Objectives. There are, on average, three people who die daily from an asthma attack in the UK. As... more Objectives. There are, on average, three people who die daily from an asthma attack in the UK. Asthma self-management and good adherence can reduce this rate of mortality. Since adherence to preventative medication is important for many people with asthma, we investigated asthma patients' and non-patients’ perceptions about asthma, the similarities between themes in interviews and on Twitter and potential influence on adherence. Design. Both patients' and non-patients' perceptions about asthma were examined in a combination of interviews and content analysis of Twitter data.Methods. Fourteen semi-structured interviews were conducted and analysed using thematic analysis; A coding instrument was developed to capture perceptions on Twitter and a content analysis was conducted on 3.000 tweets. Convergence analysis identified similar topics between interviews and social media data analysis and where these were similar or different. Results. Several themes emerged from intervi...
2021 IEEE International Conference on Big Data (Big Data)
2020 IEEE International Conference on Big Data (Big Data), 2020
The links between anxiety (and negative mental heath outcomes in general) and socio-economic cond... more The links between anxiety (and negative mental heath outcomes in general) and socio-economic conditions have been the subject of a large number of studies. However, the underlying mechanisms that affect this relationship have not been fully elucidated, nor have they been extended to consider potential mediators in the form of individual differences/psychological traits. Interrogating over 8-million customers’ loyalty card transactions from a major health retailer, this paper investigated two ideas: the potential to use health product purchases to detect anxiety distributions across geo-spatial regions in England; and exploring the relationship between these product health purchases, deprivation levels and personality traits. Specifically, this analysis examined the co-variation between: anxiety purchases within district level geo-spatial regions in the UK; mean deprivation levels; and personality traits, across those districts. Contrary to previous findings, results demonstrated a n...
Frontiers in Psychology
Behavioural scientists have been studying public perceptions to understand how and why people beh... more Behavioural scientists have been studying public perceptions to understand how and why people behave the way they do towards climate change. In recent times, enormous changes to behaviour and people’s interactions have been brought about by the worldwide coronavirus disease 2019 (COVID-19) pandemic, unexpectedly and indefinitely; some of which have environmental implications (e.g., travelling less). An innovative way to analyse public perceptions and behaviour is with the use of social media to understand the discourse around climate change. This paper focuses on assessing changes in social media discourse around actions for climate change mitigation over time during the global pandemic. Twitter data were collected at three different points during the pandemic: February (time 1), June (time 2), and October 2020 (time 3). By using machine learning techniques, including recurrent neural networks (RNN) and unsupervised learning Latent Dirichlet Allocation (LDA) topic modelling, we iden...
2020 IEEE International Conference on Big Data (Big Data), 2020
Patients’ perceptions about their condition have a strong impact on not only adherence to medicat... more Patients’ perceptions about their condition have a strong impact on not only adherence to medication, but also on how they view themselves in the light of their condition. Research implies that Twitter is a particularly rich source of perceptions, as patients frequently use internet for information sharing and support. However, Twitter contains a lot of noise in the form of tweets that do not relate to perceptions, but are rather generated to advertise research and corporate news and this kind of information could ‘pollute’ perception analysis. This study examined methods that could be used to extract perception tweets, on the example of tweets related to asthma. We first demonstrated differences between perception and non-perception tweets in terms of their linguistic features, and then focused on filtering perceptions using the classification process. Results demonstrated that there is a significant difference between perceptions and non-perceptions: perception tweets are shorter,...