My central research question is how the specific methods I chose could help mitigate the spread of infectious disease in sub-Saharan Africa, and how populations that are underrepresented or left out of the algorithms used could still benefit from the data science techniques. This would be a combination of a difference research question and an evaluative question since it involves investigating the differences between two groups: Well represented populations and the underrepresented populations; and it also seeks to explain why certain methods would be useful for aiding the development problem that I chose, which is evaluating particular practices. However, I would classify my research question as being more on the evaluative side since it looks more at the impact of techniques, including how those techniques differ between different groups, more so than just highlighting the difference between two groups. The main topic that concerns my central research question is not to identify the difference between well represented and underrepresented populations, but to explain how data science techniques can help a region, with consideration for the underrepresented populations. This makes my question lean more towards evaluative even though it does comprise significant elements of a difference question. As a result, I am considering my question to be evaluative.

One sub-topic would be what are the potential benefits of data science techniques in mitigating the spread of infectious disease? This addresses the first part of my question, and is its more evaluative side. In addition, it will comprise most of the information I give so it will be the majority of my paper. My other sub-question also relates to data science techniques, so this section of my central research question is the first part of my points. A second sub-topic would be how underrepresented populations can still be included in data science techniques and data sets? This is the more complex half of my question, and relies on the first sub-question so I am considering it to be a less significant part of my central research question, although this may change as I begin writing. This sub-question does concern the gap that I found during my research, so it should comprise mostly my own ideas, rather than using previous studies and research methods and applying them to the context of sub-Saharan Africa.