How to Analyze Survey Data in Excel With Cloud AI (Full Transcript)

[00:00:00] Speaker 1: You can use Cloud AI to help you to analyze your qualitative data, right? You can just upload your transcripts or your open-ended survey data. You can upload it and then you can also prompt the system to help you to analyze the data so that you can address your research question. But there's another way that you can do that. So imagine that you have your open-ended survey data here, right, in a self-spreadsheet. And then you want to analyze it in a self-spreadsheet with the help of Cloud AI. How are you going to do that? So let me give you a little background about the data that I'm going to use. So as you can see here, I have two main research questions, right? I have the qualitative research question and a quantitative research question. And I have a survey data. As you can see here, it's about mental health stigma and participants who are mental health providers completed the survey, open-ended the survey. And also their cultural intelligence score was also collected. So now you have qualitative data, which is open-ended responses, and then quantitative data, which is their scores concerning their cultural intelligence. So as you can see in the research question here, the first research question I want to find out mental health stigma causes and contributing factors, right? And then the second one I want to find out mental health stigma solutions, right? And the quantitative research question, one of them is what is the effect of gender on cultural intelligence? And then the second one is what is the effect of education on cultural intelligence? So we have a self-spreadsheet where the demographic information is here, the open-ended responses are here, and then we have scores for their cultural intelligence, right? So how do you use Cloud AI to help you to analyze this data in Excel? It's very simple. So the first thing that you have to do is go and click on add-in, right? And you search for Cloud, right? So as I can see, I'm searching for Cloud. So you see Cloud and then you click on add, and then it will show at the right corner of Excel spreadsheet, right? So as you can see here, I have Cloud AI here. Now, if you want to use Cloud AI in Excel spreadsheet, you can just click on that, and then you can start a conversation. And it will ask you to log in. So this means that you have to have an account with Cloud AI so that you'll be able to use it in Excel spreadsheet. So imagine that you have already logged in. This is what you're going to see. And then you can start asking the system questions so that it will be able to analyze your data for you. So what we can first add here is that you can ask the system about demographics. But before you do that, you have to give the system some background information. One thing that you have to really do at the beginning is to let the system know what this data is all about, and giving it some background information so that it will be able to provide you rich information. So as you can see here, I said before I ask you to complete any task, I want to provide you what this data is about. It is a survey data with open-ended responses and participant scores on their cultural intelligence. Data was collected from mental health providers to explore their perspective about mental health stigma, including the levels of cultural intelligence. So as you can see here, I just want to provide the system background information before I ask it to analyze the data for me. So this is what I've done now. So after clicking the enter, you can see that now the system really understands what exactly the data is about. It's trying to review and giving it understanding about the data. So now the next step is to ask it to do some analysis. So let's start with the quantitative analysis right before you start with the qualitative. Let's start with the quantitative one. So we want to find out whether there is an effect of gender on cultural intelligence. So let me copy this question and see what we're going to get. I put a question here and then now the system will be able to think through and analyze the cultural intelligence score and then try to find out whether there's a significant difference between the male and the female concern in cultural intelligence. So you see that the system has opened a new sheet here and then it's putting some information here. So it's technically acting as an agent. It's doing things on your behalf. I just asked the system a question, what is the effect of gender on cultural intelligence and then it's provided this information for me. So as you can see here, it's giving you a descriptive statistics. We can see that the mean score for the cultural intelligence for the male is 3.93 and then the mean score for the female is 3.72. We can see that the males slightly perform better than this female but the question is, is this statistically significant and this is where inferential statistics. So the system is going to perform t-tests to find out whether there's a significant difference between these two groups that we have. So you see that it's performing the t-test and let's see what we're going to get. So you see here that the mean difference is 0.7, 0.2119. I think it's just showing that the difference between the scores for men and women and then I put them here. Statistics, what we are interested in the p-value. You see the p-value here is 0.4684. This is more than 0.05. So it shows that it's not statistically significant differences between the male and female concerning the cultural intelligence or you can say that there's no significant effect of gender on their cultural intelligence scores. You can review and then see whether everything is right. If you don't understand, you can always access the system questions and you'll be able to get more information and it also provides you a chart here. This is a bar chart and seeing the scores. Let's try and find out the second quantitative research question and see what are we going to get. So this is the second one. What is the effect of education on cultural intelligence? So we're going to find out whether there's a significant difference between the educational level and with respect to their cultural intelligence. So it's doing the analysis and then let's see what are we going to get. So here it's showing that we have five levels, educational levels. So in this case because we have five, the system is saying that we're going to do a one-way ANOVA. So ANOVA is done when you have more than two groups. So we have five groups now. So we have to do an ANOVA. So you see how the system is explaining the process to you and then it has opened a new sheet and it's going to give us the result. It starts with a description statistics about the educational level. It's going to give you the scores for mean score for each of the groups that we have. So as you can see here we have 3.5 for high school and we have 4.4 for associate degree and then we have 3.6, 3.6 again for the bachelors and also masters and 3.7. And so we can see that associate degree had 4.4. Interesting. So as you can see here the p-value here is 0.35 which is more than the significant level which is 0.05. So because of that then there's no significant effect of education on cultural intelligence. And there's also provided some assumptions. If you are not familiar with this you can always ask the system to get more information. So as you can see here it has shown us the bar chart and you can see that the associate degree had the highest in terms of cultural intelligence compared to the rest of the group. Right. The second highest is I think is doctoral degree. Right. So and you can also ask the system to create a new chart for you. Maybe a pie chart. You can ask and then it will be able to do that for you. Let's move on to the qualitative research questions. Let's start with the first one. How they perceived the causes and contributing factors to mental health stigma. I think what you always have to think about is if you want the system to follow a specific qualitative data analysis strategy you can let a system know about it and to be able to follow. If you want the system to make assumptions and make the decision by itself about the kind of analysis you can just put in the research question and then the system will be able to do the analysis on your behalf. But it's always good to give the system the kind of analysis you want it to do. So in this case I can say can you on that thematic analysis to help address the following research question. So I want the system to follow the six phases of reflexive thematic analysis and addressing this research question. Right. So let's see what a system will do for us. So it has identified the places that it will want to analyze. There's a place that they will ask about the perceived causes of mental health stigma and also the contributing factors. So it's going to analyze these two columns to help to address the research question provided. So as you can see here it has identified the six steps from analyzing WIC data. So it's reviewing the data to get overall understanding about participant responses and then it will move to the second phase which is generating initial code. And then it will move to the next stage, the next phase which is searching for themes and then reviewing the themes making sure that they're addressing the research question and defining the name in the theme and then writing the report. So because it's following all these steps and it has to show it work it will take some time for the system to complete the tasks that you are asking it to do. So you can even leave the system for a while and then you can come back and see whether it has completed the tasks that you asked it to complete. So it looks like it has finished the phase one here. It has gone through the data now it's almost done with I think it's done with phase two generating initial codes and then you see all the codes in a description and also providing example of the SFs and then a number of times significant information is connected to the codes and then you move on to searching for themes. So you can see that the first one, the first candidate, the second candidate. So these are the potential themes and then it moves on to review the themes and then providing information about the decision making process. That's what I like about cloud and then you can see that we're in phase five which is defining and naming the themes the system has been able to define. So these are the themes. So one of the themes addressing the research question is knowledge deficit and educational gap and then it has provided the definition. It also provided some of the key codes that are connected to that and also the number of significant information that was extracted and connected to this theme and then you can see that we have about seven themes in terms of the causes and the contributing factors and then this is once you write in a report. So you can see that it has provided information about the theme here and then you're given a narrative description which is giving information what a theme represents what are the main characteristics of the theme and also provide a quotation that are connected to the theme. So you can also use this one to help you to present your finding and all these are suggestions you can always review and make the necessary corrections and the system can make mistakes so you always have to check are these quotations from the data that you gave to the system right. So you have to check and review and make sure everything is right make an adjustment when needed. So then it has also provided us a table here showing the number of participants that are connected to their theme right. So I think I maybe I made a mistake here let me go back again and say so you see here it's not a number of quotations the number of participants you see here the number of participants connected to the theme. So it looks like we have seven themes and then the system gave overall conclusions right. So you see how the system has provided you all the information that you need for you to review and also making sure that they really reflect the data that you have. So we can do the same thing for the second research question the quantitative research question it might go through the same process and provide you the information that you need. This is what I have for you let me know whether you have any questions I'll be happy to address them for you. Thank you so much for your time.