LSBU Library: How to Use Artificial Intelligence: 4. AI for Study and Research

Skills for Success / Academic Skills / How to Use Artificial Intelligence

4. AI for Study and Research

(Full text is below the infographic)

AI for Study and Research

AI is a valuable tool for university students. Use it to learn more effectively, increase your productivity, and get better results.

Tutoring

AI can act as your personal tutor, providing support in subjects where you might need extra help, explaining things, setting you practice problems, and giving instant feedback.

Personalised Learning

AI can tailor content and feedback to your level, learning style, and pace, helping you understand complex topics more deeply.

Study Assistance

AI can help you with notetaking, summarising lectures and articles, and it can answer your questions.

Searching the Literature

AI can help you

search for books, articles and data, saving you time and helping you find the best sources in your field.
interpret research papers, making it easier to understand the key findings and methodologies without reading the entire document.

Paraphrasing and Summarising

AI can help you paraphrase short texts and summarise longer texts such as articles or papers to grasp the main points quickly.

Citations and References

AI can help you manage your references, format them correctly, and create Reference sections in the style you have to use.

Planning

AI can suggest ways to structure your academic essays, reports, presentations, etc.

Data Analysis

AI tools can help when you have to analyse large amounts of data, for example, identifying patterns and generating insights.
AI provides guidance on using tools like Excel and SPSS for data analysis.

Explaining Statistical Methods

Copilot can recommend resources, such as textbooks, online courses and tutorials, to help you deepen your understanding of statistics.
An AI such as Copilot can explain various statistical methods, such as hypothesis testing, regression analysis and ANOVA to help you understand how and when to use them.
It can help with solving statistical problems and exercises.
It can provide step-by-step explanations and solutions.
AI can help you interpret what statistical software produces, such as p-values, confidence intervals, and regression coefficients.

Interpreting Results

AIs, such as Copilot, can help you interpret the results of your data analysis, explaining what the numbers mean and how to draw meaningful conclusions from them.

Data Visualisation

AI can suggest ways to visualise your data effectively using charts, graphs, and other visual aids to make your results more understandable and impactful.

Example of how Copilot can help with data analysis

Glenda, a business student, conducted a questionnaire to explore customer preferences in a local coffee shop. Her questionnaire gathered data on variables like age, gender, frequency of visits, favourite drink, average spend per visit, and satisfaction level.

Glenda logs in to her LSBU student account and uploads her data to Copilot. She wants to know if satisfaction differs significantly by gender, so she asks:

Here is my data about coffee shop customer satisfaction. How do I find out if males or females are more satisfied, and how do I know if it is a significant difference and not just random?

Respondent ID	Age	Gender	Visits/Month	Favourite Drink	Av. Spend (£)	Satisfaction (1-10)
001	25	Female	10	Latte	5.50	8
002	32	Male	6	Cappuccino	4.75	7
003	19	Female	12	Mocha	6.00	9
004	45	Male	4	Americano	3.50	6
005	28	Female	8	Cold Brew	5.25	8
006	37	Male	5	Latte	4.25	7
007	22	Female	15	Frappuccino	6.75	10
008	29	Male	7	Mocha	5.00	8
009	40	Female	3	Americano	3.25	6
010	34	Male	9	Cappuccino	4.50	7
011	21	Female	14	Latte	6.25	9
012	50	Male	2	Espresso	2.75	5
013	26	Female	10	Cold Brew	5.75	8
014	31	Male	6	Frappuccino	6.50	9
015	23	Female	13	Mocha	6.00	8
016	42	Male	4	Americano	3.00	6
017	35	Female	8	Cappuccino	4.75	7
018	27	Male	9	Latte	5.25	8
019	39	Female	3	Espresso	3.75	6
020	30	Male	7	Mocha	5.50	8

Copilot answers:

To determine if males or females are more satisfied and whether the difference is statistically significant, here's a step-by-step guide:

1. Organize and Compare Average Satisfaction Scores

Group the data by gender and calculate the average satisfaction score for males and females separately:

Females: Average of satisfaction scores for all female respondents.
Males: Average of satisfaction scores for all male respondents.

This gives a basic comparison between the two groups.

2. Conduct a Statistical Test

To assess if the difference in satisfaction is statistically significant, use an independent t-test. This test compares the means of two groups and evaluates whether the observed difference is due to chance.

Steps for t-test:
- Null Hypothesis (H₀): There is no significant difference in satisfaction between males and females.
- Alternative Hypothesis (H₁): There is a significant difference in satisfaction between males and females.
- Input the satisfaction scores for both groups into a statistical tool or software (e.g., Excel, Python, R, SPSS).
- Compute the p-value:
  - If p < 0.05, reject the null hypothesis (the difference is significant).
  - If p ≥ 0.05, fail to reject the null hypothesis (the difference is not significant).

3. Use Software or Tools

Here are some tools that can help:

Excel: Use the "Data Analysis" toolpack to run a t-test.
Python: Use the scipy.stats.ttest_ind() function.
R: Use the t.test() function.

Would you like detailed help on any of these steps or assistance performing the calculations?

As usual, Copilot makes suggestions and then asks if more help is needed.

Glenda replies:

Thanks. I've pasted the satisfaction scores into Excel. What do I do now?

Copilot replies:

Great! Here's how to perform a t-test in Excel to analyze the satisfaction scores for males and females.....

Copilot then goes on to give clear step-by-step instructions for Excel which we won't go into here, but you get the idea.

True / False Question

Copilot can read an article and summarise it for you in words that you can understand.

True
False

< Previous Page

Next Page: 5. Feedback and Assessment >