ADDITIONAL MATHEMATICS SCHOOL BASED ASSESSMENT

CANDIDATES CANDIDATE NUMBER

Chelsea Sieubachan 1600660948
Elena Sudan 1600661014
Jada-Marie Pierre 1600660808
Keresse Noray 1600660700
Sierra Peters-Charles 1600660786

SCHOOL: St. Joseph’s Convent, St. Joseph

SCHOOL CENTRE NUMBER: 160066

SUBJECT: Additional Mathematics

TITLE: An Investigation into the Relationship between the

Number of Followers a Person Has on Twitter and
Their Self-Esteem

TEACHER: Ms. Denise Manchabali

TERRITORY: Trinidad and Tobago

 TITLE:
The Relationship Between the Number of Followers One has on Twitter and Their Self
Esteem
 TABLE OF CONTENTS

Introduction 1

Purpose of Project 2

Method of Data Collection 3

Presentation of Data 4

Graphical Representation of Raw Data 11

Mathematical Knowledge and Analysis of Data 13

Discussion 21

Limitations of Study 22

Conclusion 23

Suggestions for Future Analysis 24

Bibliography 25

Appendix 26
 INTRODUCTION

Oftentimes people spend multiple hours a day on Twitter. Twitter is a social media platform
that allows people to communicate and stay connected through the exchange of quick,
frequent messages. People post their thoughts and opinions and can gain followers solely
based on what they post. Self-esteem is how a person values and perceives themselves. It is
based on their opinions and beliefs about themselves. We might also think of this as
self-confidence. It may be possible that self-esteem can affect if one likes and values oneself
as a person. If people base how they view themselves on their popularity, then, their number
of followers should affect their self esteem.

1
 PURPOSE OF PROJECT

This project was aimed to investigate the relationship between the number of followers on
Twitter a person has and their self esteem. This project was chosen in order to determine
whether there is a relationship between a person's number of followers on Twitter and their
self esteem. We aimed to investigate if a link exists between perceived popularity on social
media and happiness and establish a mathematical connection between popularity on Twitter
and a person’s happiness and self esteem.

2
 METHOD OF DATA COLLECTION

Data was collected from a sample size of 100 teenagers and young adults using an online
questionnaire via google forms. All participants were instructed to truthfully answer the
questions on the survey and were not privy to the scoring rubric so as to not influence their
answers. The scoring rubric was used in order to convert qualitative data to quantitative ;
specific marks were assigned for specific responses. Once the data was collected, the self
esteem scores were tabulated. The number of followers each person had was the independent
variable while the dependent variable was the corresponding self esteem score. The link for
the questionnaire was shared to both male and female secondary school students via the social
media platform Whatsapp between Monday 16th January 2023 and Friday 27th January 2023
and convenience sampling was utilised. Secondary school students were questioned as they
are the primary demographic for social media apps like Twitter and live in the peak era of
Social Platforms. Subsequently, the survey was closed and no more data was collected. The
data utilised in this project was qualitative and using the rubric, was converted to quantitative.

3
 PRESENTATION OF DATA

TABLE 1: RAW DATA OF NUMBER OF FOLLOWERS AND SCORE ON SELF

ESTEEM QUESTIONNAIRE

Number of Followers of Social Media Score on Self Esteem Questionnaire

1 15

1 10

1 4
1 14
30 17
47 12
50 19
50 10
57 12
66 17
67 15
69 16
69 10
70 15
73 14
89 10
116 14
123 14
123 14
128 11
139 15
180 15
195 15
200 11
223 16

4
234 16
235 14
238 13
244 17
244 15
249 15
282 13
296 16
297 11
300 19
324 19
340 15
356 12
359 14
373 9
374 12
437 6
446 15
450 15
466 14
469 15
486 14
510 20
511 18
540 12
552 14
570 17
600 13
657 18
673 12
675 15
715 18

5
719 15
723 12
730 14
763 13
767 15
800 16
800 14
800 14
800 13
813 12
847 19
862 14
888 16
889 15
970 13
980 15
998 18
1000 15
1000 11
1005 16
1016 13
1017 15
1023 12
1051 14
1105 15
1150 17
1156 18
1185 12
1234 14
1257 13
1300 15
1350 16

6
1400 16
1453 16
1871 14
1895 14
2089 12
2895 17
3000 10
3000 19
3403 17
3500 15
4749 11

7
 TABLE 2: SHOWING GROUPED DATA FOR NUMBER OF FOLLOWERS AND
THEIR CORRESPONDING FREQUENCY VALUES

Class Lower Class Upper Class Midpoint, 𝑥 Frequency, 𝑓 Cumulative

Intervals Boundaries Boundaries Frequency

1 - 500 0.5 500.5 250.5 47 47

501 - 1000 500.5 1000.5 750.5 29 76

1001 - 1500 1000.5 1500.5 1250.5 15 91

1501 - 2000 1500.5 2000.5 1750.5 2 93

2001 - 2500 2000.5 2500.5 2250.5 1 94

2501 - 3000 2500.5 3000.5 2750.5 3 97

3001 - 3500 3000.5 3500.5 3250.5 2 99

3501 - 4000 3500.5 4000.5 3750.5 0 99

4001 - 4500 4000.5 4500.5 4250.5 0 99

4501 - 5000 4500.5 5000.5 4750.5 1 100

Where LCL and UCL are lower and upper class limits respectively, and LCB and UCB are
lower and upper class boundaries respectively.

Using the class interval 501-1000, where LCL= 501 and UCL= 1000 and the following class
is 1001-1500 and the preceding class 1-500

𝑢𝑝𝑝𝑒𝑟 𝑙𝑖𝑚𝑖𝑡 + 𝑙𝑜𝑤𝑒𝑟 𝑙𝑖𝑚𝑖𝑡 𝑜𝑓 𝑓𝑜𝑙𝑙𝑜𝑤𝑖𝑛𝑔 𝑖𝑛𝑡𝑒𝑟𝑣𝑎𝑙

𝑈𝐶𝐵 = 2
1000+ 1001
𝑈𝐶𝐵 = 2
= 1000. 5

𝑢𝑝𝑝𝑒𝑟 𝑙𝑖𝑚𝑖𝑡 𝑜𝑓 𝑝𝑟𝑒𝑐𝑒𝑑𝑖𝑛𝑔 𝑐𝑙𝑎𝑠𝑠 𝑖𝑛𝑡𝑒𝑟𝑣𝑎𝑙 + 𝑙𝑜𝑤𝑒𝑟 𝑙𝑖𝑚𝑖𝑡

𝐿𝐶𝐵 = 2
500+ 501
𝐿𝐶𝐵 = 2
= 500. 5

𝑈𝐶𝐵+𝐿𝐶𝐵
𝑀𝑖𝑑𝑝𝑜𝑖𝑛𝑡 = 2

1000.5+500.5
𝑀𝑖𝑑𝑝𝑜𝑖𝑛𝑡 = 2
= 750.5

8
TABLE 3: TABLE SHOWING GROUPED DATA OF SELF ESTEEM SCORES
AND THEIR CORRESPONDING FREQUENCIES

Class Interval Lower Class Upper Class Midpoint, 𝑥 Frequency, 𝑓

Boundaries Boundaries

1-3 0.5 3.5 2 0

4-6 3.5 6.5 5 2
7-9 6.5 9.5 8 1
10 - 12 9.5 12.5 11 21
13 - 15 12.5 15.5 14 48
16 - 18 15.5 18.5 17 22
19 - 21 18.5 21.5 20 6
22 - 24 21.5 24.5 23 0
25 - 27 24.5 27.5 26 0

9
TABLE 4 : TABLE SHOWING AN INDIVIDUAL’S SELF ESTEEM SCORE AND
THEIR CORRESPONDING NUMBER OF FOLLOWERS

Self Esteem Score Number of Followers

4 1

6 437

9 373

10 1, 50, 69, 89, 3000

11 128, 200, 297, 1000, 4749

12 47, 57, 356, 374, 540, 673, 723, 813, 1023,

1185, 2089

13 238, 282, 600, 763, 800, 970, 1016, 1257

14 1, 73, 116, 123, 123, 235, 359, 466, 486,

552, 730, 800, 800, 862, 1051, 1234, 1871,
1895,

15 1, 67, 70, 139, 180, 195, 244, 249, 340, 446,

450, 469, 675, 719, 767, 889, 980, 1000,
1017, 1105, 1300, 3500

16 69, 223, 234, 296, 800, 888, 1005, 1350,

1400, 1453

17 30, 66, 244, 570, 1150, 2895, 3403

18 511, 657, 715, 998, 1156

19 50, 300, 324, 847, 3000

20 510

10
 GRAPHICAL REPRESENTATION OF RAW DATA

Equation of the best fit line was calculated using the points from the line (235,14) and
(3500,15)
𝑦2−𝑦1
𝑚= 𝑥2−𝑥1
15−14
𝑚= 3500−235
1
𝑚= 3265
= 0. 000306

𝑦 = 𝑚𝑥 + 𝑐
15= 0.000306 (3500) + c
15-1.071= c
c= 13.929

y=mx+c
y=0.000306x + 13.929
Where m= 0.000306 and c= 13.929

Using x=1895, Using x=359

y= 0.000306(1895) + 13.929 y= 0.000306(359) + 13.929
y=14.50887 y=14.038854

From questionnaire 1895 followers had a score of 14 and 359 followers had a score of 14
thus, the equation of the line is accurate.

11
GRAPHICAL REPRESENTATION OF GROUPED DATA

12
 MATHEMATICAL KNOWLEDGE AND ANALYSIS OF DATA

Based on the Curve:

Lower Quartile:
= ¼ (n)
= ¼ (100)
=25th position
Score = 13

Upper Quartile:
=¾ (n)
=¾ (100)
=75th position
Score = 16

Median:
=½ (n)
=½ (100)
=50th position
Score = 14

13
Modal Score:

From the Histogram above,

Modal score = 14

14
Mean Score, 𝑥̅:

Using Values From Table 3:

Class Interval Lower Class Upper Class Midpoint, 𝑥 Frequency, 𝑓

Boundaries Boundaries

1-3 0.5 3.5 2 0

4-6 3.5 6.5 5 2
7-9 6.5 9.5 8 1
10 - 12 9.5 12.5 11 21
13 - 15 12.5 15.5 14 48
16 - 18 15.5 18.5 17 22
19 - 21 18.5 21.5 20 6
22 - 24 21.5 24.5 23 0
25 - 27 24.5 27.5 26 0

= ∑𝑓𝑥 ÷ ∑ƒ

= [(0×2)+(2×5)+(1×8)+(21×11)+(48×14)+(22×17)+(6×20)+(0×23)+(0×26)]÷100

= 14.15

∴ 𝑥̅ = 14.15

15
 TABLE SHOWING SCORE VARIATION CALCULATIONS

Class ƒ 𝑥 𝑥-x̅ (x-x̅)² ƒ(𝑥-x̅)²

Intervals

1-3 0 2 2-14.15=-12.15 147.6 0

4-6 2 5 5-14.15=-9.15 83.7 167.4

7-9 1 8 8-14.15=-6.15 37.8 37.8

10-12 21 11 11-14.15=-3.15 9.9 207.9

13-15 48 14 14-14.15=-0.15 0.0225 1.08

16-18 22 17 17-14.15=2.85 8.12 178.64

19-21 6 20 20-14.15=5.85 34.2 205.2

22-24 0 23 23-14.15=8.85 78.3 0

25-27 0 26 26-14.15=11.85 140.4 0

Variance, s2:
= ∑ƒ(𝑥-x̅)²÷n
=(0+167.4+37.8+207.9+1.08+178.64+205.2+0+0)÷100
=7.98

Standard Deviation, s:
= √∑ƒ(𝑥-x̅)²÷n
=2.8

16
For no. of followers:

Using the Cumulative Frequency Curve:

Based on the curve

Lower Quartile:
¼ (n)
¼ (100)
=25th position
=223 followers

Median:
½ (n)
½ (100)
=50th position
=540 followers

Upper Quartile:
¾ (n)
¾(100)
=75th position
=1000 followers

17
Modal no. of followers:

From the histogram above,

Mode = 390 followers

18
Mean, 𝑥̅:

Using Values From Table 2:

Class Lower Class Upper Class Midpoint, 𝑥 Frequency, 𝑓 Cumulative

Intervals Boundaries Boundaries Frequency

1 - 500 0.5 500.5 250.5 47 47

501 - 1000 500.5 1000.5 750.5 29 76

1001 - 1500 1000.5 1500.5 1250.5 15 91

1501 - 2000 1500.5 2000.5 1750.5 2 93

2001 - 2500 2000.5 2500.5 2250.5 1 94

2501 - 3000 2500.5 3000.5 2750.5 3 97

3001 - 3500 3000.5 3500.5 3250.5 2 99

3501 - 4000 3500.5 4000.5 3750.5 0 99

4001 - 4500 4000.5 4500.5 4250.5 0 99

4501 - 5000 4500.5 5000.5 4750.5 1 100

= ∑𝑓𝑥 ÷ ∑ƒ

=[(47×250.5) + (29×750.5) + (15×1250.5) + (2×1750.5) + (1×2250.5) + (3×2750.5) +

(2×3250.5) + (0×3750.5) + (0×4250.5) + (1×4750.5)] ÷ 100

=752.995 followers

∴ 𝑥̅ = 752.995

19
 TABLE SHOWING FOLLOWER VARIATION CALCULATIONS

Class Intervals 𝑓 𝑥 𝑥-x̅ (𝑥-x̅)2 ƒ(𝑥-x̅)2

1-500 47 250.5 250.5-752.995=-502.5 252,501.23 11,867,557.6

501-1000 29 750.5 750.5-752.995=-2.495 6.23 180.67

1001-1500 15 1250.5 1250.5-752.995=497.5 247,511.23 3,712,668.4

1501-2000 2 1750.5 1750.5-752.995=997.505 995,016.23 1,990,032.46

2001-2500 1 2250.5 2,250.5-752.995=1,497.5 2,242,521.23 2,242,521.23

2501-3000 3 2750.5 2750.5-752.995=1,997.05 3,990,026.23 11,970,078.68

3001-3500 2 3250.5 3250.5-752.995=2,497.5 6,237,531.23 12,475,062.46

3501-4000 0 3750.5 3750.5-752.995=2,997.505 8,985,036.23 0

4001-4500 0 4250.5 4250.5-752.995=3,497.5 12,232,541.23 0

4501-5000 1 4750.5 4750.5-752.995=3,997.5 15,980,046.23 15,980,046.23

Variance, s2:
= ∑ƒ(𝑥-x̅)²÷n
=(11,867,577.6+180.67+3,712,668.4+1,990,032.36+2,242,521.23+11,970,078.68+12,475,06
2.46+0+0+15,980,046.23) ÷100
=60,238,147,73÷100
=602,381.4773

Standard Deviation, s:
=√∑ƒ(𝑥-x̅)²÷n
=776.132

20
 DISCUSSION

This investigation aimed to determine whether there is a relationship between a person’s

number of followers and their self esteem. In order to establish this, the lower quartile,
median, upper quartile, variance, standard deviation, mean, and mode were calculated for the
self esteem score.

The median provides a helpful measure of the centre of a dataset. By comparing the median
to the mean, one can get an idea of the distribution of a dataset. When the mean and the
median are the same, the dataset is more or less evenly distributed from the lowest to highest
values. The mode or modal value of a data set is the most frequently occurring value. It's a
measure of central tendency that indicates the most popular choice or most common
characteristic of a sample. It is the best measure of central tendency for highly skewed data
since it is not affected by extreme values. Finding an average gives an idea as to an overall
behaviour or trend. Like the median and the mode, the average is a measure of central
tendency, meaning it reflects a typical value in a given set. Standard deviation is important
because it helps in understanding the measurements when the data is distributed. It tells us
how spread out the values are in a given dataset. Variance is a measurement of the spread
between numbers in a data set. In particular, it measures the degree of dispersion of data
around the sample's mean. The trendline indicates a linear relationship, illustrates trends in a
data set and can make charting predictions, while the gradient indicates proportionality, i.e. a
positive gradient indicates that when one variable increases/decreases, the other variable
increases/decreases respectively whereas a negative gradient indicates that as one variable
increases/decreases, the other variable decreases/increases respectively. Skewness is a
measure of the asymmetry of a distribution. The average value of self esteem was 14.26 out
of 27 while the modal score was 14. The median was 14. The lower quartile value was a score
of 13 and the upper quartile was 16. The standard deviation of the scores was 2.8 while the
variance was found to be 7.98. The average number of followers was 752.995, the modal
number was 390, the median was 540. The lower quartile was 223 while the upper quartile
was 1000. The standard deviation of the number of followers was 776.132 and the variance
was found to be 602,381.4773. The average self esteem score was a representation of all the
values in the respective data sets. From the histogram for self esteem scores, the data was
observed to be symmetrical whereas the data for the number of followers is positively
skewed. In the scatter plot shown, a straight line with a positive gradient (0.000306) was
observed which showed that as the number of followers a person had increased, so did their
self esteem. Thus, the number of followers and self esteem are related. The equation of the
best fit line was y=0.000306x+13.929. Our data shows that while the self-esteem scores of
teenagers are relatively low, the more followers they had, the higher their scores. The line of
best fit positive gradient, indicating that as a person's number of followers increased, so did
their self esteem score.

21
 LIMITATIONS OF STUDY

1. Only secondary school students were questioned, thus the data set was limited which
may have led to inaccurate results.

2. Only followers from the social media platform “Twitter” were taken into account, thus
not providing an accurate representation of all of a person’s followers across different
apps which may have led to inaccurate results.

3. Since self esteem is qualitative data, not quantitative, the rubric may not be sufficient
in assigning a score to a person's self esteem. The persons questioned may also have
chosen answers with the intent of achieving a higher score which would have biassed
the results.

22
 CONCLUSION

Based on the trendline of the scatter plot, which had a gradient of +0.000306, as the number
of followers increased, one’s self esteem score also increased. The gradient of the line was
positive so as the x values (no. of followers) increased, the y values (self esteem score) also
increased. Based on this experiment, it was concluded that there is in fact a relationship
between number of followers and self esteem, i.e. as the number of followers increases, self
esteem also increases. In sum, the purpose of the project was met as a mathematical link
between number of followers and self esteem was established.

23
 SUGGESTIONS FOR FUTURE ANALYSIS

The standard deviation and variance show the distribution of data in a data sample with
reference to the mean. Therefore, having a larger sample size increases the accuracy of the
standard deviation and variance derived from it. If this SBA was to be carried out a second
time, a larger sample size would be recommended in order to make the results more reliable
and less skewed by reducing the margin for error. If the S.B.A. were to be redone and if one
hopes to change qualitative data to quantitative, one can do so using a more rubric that
accurately assigns a numerical value to intangible, uncountable things with greater precision
than the rubric used in this S.B.A., a rubric which takes into account any psychological
factors which may be involved with the group of people surveyed. Furthermore, when social
media following is being taken into consideration, whether an account is private or public
should be acknowledged. Similar studies can be conducted to establish relationships between
other things. They can be used in
● Psychological studies
● Employee surveys
For example, the number of hours spent on social media and happiness. This goes to show
that once qualitative data is converted to quantitative, the data can be analysed and compared
to another set of quantitative data. Since our self esteem affects our mental health, studies like
this can be used by psychologists to determine whether or not apps like Twitter are healthy or
whether they cause more harm than good and whether or not specific apps should be made
available to the younger population.

24
 BIBLIOGRAPHY

https://www.techtarget.com/whatis/definition/Twitter
https://www.verywellmind.com/what-is-self-esteem-2795868
http://www.alcula.com/calculators/statistics/box-plot/

25
 Appendix

The questionnaire for the investigation was as follows:

1. Are you active on Social Media? YES or NO.

2. How many friends or followers on Social Media do you have?

(PLEASE SPECIFY)

3. Physical Attractiveness plays into how many Social Media friends and followers
a person has.
a) Strongly Agree
b) Agree
c) Disagree
d) Strongly Disagree

3. Browsing my profile (my wall posts, statuses and pictures) affects my self-esteem.
a) Strongly Agree
b) Agree
c) Disagree
d) Strongly Disagree

4. I feel like Facebook, Instagram, Snapchat, Twitter etc. is a competition to earn the most
friend requests, likes and comments.
a) Strongly Agree
b) Agree
c) Disagree
d) Strongly Disagree

5. I feel a confidence boost when someone ‘likes’ something of mine on Social Media.
a) Strongly Agree
b) Agree
c) Disagree
d) Strongly Disagree

6. I talk to people more on Social Media than I do in person.

a) Strongly Agree
b) Agree
c) Disagree
d) Strongly Disagree

26
7. Browsing other people’s statuses, pictures, relationship updates etc. lowers my self-
esteem.
a) Strongly Agree
b) Agree
c) Disagree
d) Strongly Disagree

8. I have more negative feelings (jealous, depressed, lazy, angry, procrastinating) when I
spend an extended period of time on Social Media.
a) Strongly Agree
b) Agree
c) Disagree
d) Strongly Disagree

9. People who have many friends on Facebook, Instagram etc. are more confident than
people who don’t have any friends.
a) Strongly Agree
b) Agree
c) Disagree
d) Strongly Disagree

The scoring rubric was as follows:

For question 1:
YES=3 points
NO=0 points

For question 2, no points were allotted.

For questions 4, 6, 7:
Strongly Agree = 3 points
Agree = 2 points
Disagree = 1 point
Strongly Disagree = 0 points

For questions 3, 5, 8, 9, 10:

Strongly Agree = 0 points
Agree = 1 point
Disagree = 2 points

27
Strongly Disagree = 3 points

28