First look: understanding vaccination sentiments and intent using big data analytics for public health management
In Malaysia, decline in vaccination have been reported with experts pointing out the causal factors such as religious grounds, autism scare, and believing anti-vaccination theories spread on the internet and social media networks. Electronic Word-of-Mouth (eWOM), especially negative sentiments perta...
| Main Author: | |
|---|---|
| Format: | Dissertation (University of Nottingham only) |
| Language: | English |
| Published: |
2018
|
| Online Access: | https://eprints.nottingham.ac.uk/54325/ |
| _version_ | 1848799037718790144 |
|---|---|
| author | Kiew, David Chai Nguan |
| author_facet | Kiew, David Chai Nguan |
| author_sort | Kiew, David Chai Nguan |
| building | Nottingham Research Data Repository |
| collection | Online Access |
| description | In Malaysia, decline in vaccination have been reported with experts pointing out the causal factors such as religious grounds, autism scare, and believing anti-vaccination theories spread on the internet and social media networks. Electronic Word-of-Mouth (eWOM), especially negative sentiments pertaining to vaccination has implicated an increase of vaccination refusal by parents, resulting in the incidence of vaccine preventable diseases such as diphtheria to spike, leading to death cases. Health authorities have traced nearly 1600 children that did not receive vaccination in the year 2016 compared to 1500 in the year 2015. Older vaccine preventable diseases like polio and tuberculosis that were once contained through vaccinations have now reemerged. The Malaysia Ministry of Health (MOH) has acknowledged the growing trend of social media usage that affects vaccination decisions. The propagated network effect on the increase of refusal to vaccinate poses a serious public health risk. The use of big data, notably predictive text analytics, to analyse the Electronic Word-of-Mouth (eWOM) in social media on vaccines to derive insights and behavioural intent using a conceptualized framework has been implicated in this study. 2511 data lines have been captured and divided into 2 datasets based on disease transmission factor. The final datasets were analysed using SAS Texts Analytics and SAS Visual Analytics. The results showed higher negative sentiments compared to positive sentiments, which were consistent with the increase of vaccination refusal. Sentiment drivers have been derived for both datasets and conceptualized frameworks were built based on the Extended Theory of Planned Behaviour. The generated insights and recommendations may improve health policy management, communication or campaigns, and pivot the overall vaccination sentiments to a positive light. |
| first_indexed | 2025-11-14T20:29:18Z |
| format | Dissertation (University of Nottingham only) |
| id | nottingham-54325 |
| institution | University of Nottingham Malaysia Campus |
| institution_category | Local University |
| language | English |
| last_indexed | 2025-11-14T20:29:18Z |
| publishDate | 2018 |
| recordtype | eprints |
| repository_type | Digital Repository |
| spelling | nottingham-543252019-02-08T13:00:48Z https://eprints.nottingham.ac.uk/54325/ First look: understanding vaccination sentiments and intent using big data analytics for public health management Kiew, David Chai Nguan In Malaysia, decline in vaccination have been reported with experts pointing out the causal factors such as religious grounds, autism scare, and believing anti-vaccination theories spread on the internet and social media networks. Electronic Word-of-Mouth (eWOM), especially negative sentiments pertaining to vaccination has implicated an increase of vaccination refusal by parents, resulting in the incidence of vaccine preventable diseases such as diphtheria to spike, leading to death cases. Health authorities have traced nearly 1600 children that did not receive vaccination in the year 2016 compared to 1500 in the year 2015. Older vaccine preventable diseases like polio and tuberculosis that were once contained through vaccinations have now reemerged. The Malaysia Ministry of Health (MOH) has acknowledged the growing trend of social media usage that affects vaccination decisions. The propagated network effect on the increase of refusal to vaccinate poses a serious public health risk. The use of big data, notably predictive text analytics, to analyse the Electronic Word-of-Mouth (eWOM) in social media on vaccines to derive insights and behavioural intent using a conceptualized framework has been implicated in this study. 2511 data lines have been captured and divided into 2 datasets based on disease transmission factor. The final datasets were analysed using SAS Texts Analytics and SAS Visual Analytics. The results showed higher negative sentiments compared to positive sentiments, which were consistent with the increase of vaccination refusal. Sentiment drivers have been derived for both datasets and conceptualized frameworks were built based on the Extended Theory of Planned Behaviour. The generated insights and recommendations may improve health policy management, communication or campaigns, and pivot the overall vaccination sentiments to a positive light. 2018-02-24 Dissertation (University of Nottingham only) NonPeerReviewed application/pdf en https://eprints.nottingham.ac.uk/54325/1/54325-David%20Kiew%20Chai%20Nguan.pdf Kiew, David Chai Nguan (2018) First look: understanding vaccination sentiments and intent using big data analytics for public health management. [Dissertation (University of Nottingham only)] |
| spellingShingle | Kiew, David Chai Nguan First look: understanding vaccination sentiments and intent using big data analytics for public health management |
| title | First look: understanding vaccination sentiments and intent using big data analytics for public health management |
| title_full | First look: understanding vaccination sentiments and intent using big data analytics for public health management |
| title_fullStr | First look: understanding vaccination sentiments and intent using big data analytics for public health management |
| title_full_unstemmed | First look: understanding vaccination sentiments and intent using big data analytics for public health management |
| title_short | First look: understanding vaccination sentiments and intent using big data analytics for public health management |
| title_sort | first look: understanding vaccination sentiments and intent using big data analytics for public health management |
| url | https://eprints.nottingham.ac.uk/54325/ |