Survey is the vital issue of data driven research. Data based research outcome depends on the quality and reliability of your data. That’s why it is important to focus on thought and planning. To design a great survey we need to follow some guidelines. In this article, I will focus on how you can design a great survey regarding your data driven research. For designing a great survey we have to focus on eight things.
➢ Focus on your objectives
➢ Concentrate your efforts on a particular audience.
➢ Create a survey structure
➢ Choose your survey’s mode
➢ Select the appropriate question type
➢ Prepare your questions
➢ Introduce the survey
➢ Take the field
Focus on your objectives:
What will be the purpose of your survey? It should be clear and understandable. Otherwise when you will design your survey it will not be an effective survey and your research goal also will not be understandable. It sets the direction for everything you do. So before going to the design of the survey, we need to set the goals. “Prediction of good CGPA using Machine Learning” is an example of a clear, productive goal. We’ll see how this goal applies to every component of the survey as we progress through the next sections.
Concentrate your efforts on a particular audience:
When it comes to data collection, it’s essential to reach out to the proper people. Another most important part of data collection is identifying the right sample. The nature and phrasing of the questions included in the questionnaire are also highly influenced by the target group. The target in the case of the example we’ve taken here would be the working population of the university from 1st year to fourth year students. That means we are working on students’ performance, we need to select only students as a target audience.
Create a survey structure:
Participants will find it easier to navigate a questionnaire if it is divided into categories. Particular sections, such as personal information, and Impact Assessment sections, such as Social, Educational, Behavioral, Mental, Physical, and Cultural, for example, will provide the survey a logical flow that will make it easier to interpret.
Choose your survey’s mode:
The method you use to conduct the survey is determined by the sample size and type. Use the most effective methods for reaching your core audience. The length of the research is also a component that influences this decision. Choosing the wrong survey method, for example, can endanger your research. Launching a web-based survey that requires participants to visit a website in order to answer the questionnaire will be almost useless when trying to reach folks in villages with little or no internet availability, for example.
Select the appropriate question type
In any activity, using the correct tools for the job is essential. Your survey’s tools are questions, and choosing the wrong question type can be as inconvenient as making a sweater with a hammer.
Prepare your questions:
Before sending out the survey, be precise about what you require and have your questions proofread by someone who isn’t familiar with your study. For example, If you ask your audience to rate their degree of satisfaction on a scale of 1 to 5, but don’t clarify whether 1 means highly satisfied or 5 means very satisfied, their answers will be meaningless.
Introduce the survey:
After reading the introduction, the audience would like to participate in the survey. As a
result, the introduction must establish a solid, strong first impression.
Take the field
Once the survey is completed, follow out your ideas with the help of a dependable data collection system. If the survey will be conducted in person, make sure the persons who will be conducting it are well-informed about the survey’s purpose and are comfortable conversing with the people they will be engaging with. Online surveys can be undertaken, but keep audience data secret and test the survey with a small control group to ensure that everything works as expected.
Md. Mahfujur Rahman has completed his B.Sc. and M.Sc. degree from Jahangirnagar University. Currently, He is working as a Sr. Lecturer at the Department of Computer Science at Daffodil International University. Besides, He is also working as a member at ProConf and Co-founder of ProConf. In his 5 years of practical experience in the Information Technology (IT) field, he completed more than 10 successful projects and 22 research papers. His research area covered Blockchain, Software Engineering, Machine Learning, Deep Learning. He is a Cisco Certified Network Associate(CCNA) and Certified Database Designer and Implementation with Web Applications. He is a Graduate member of IEEE.