Analyzing Facebook Comments: A Data Science Project for BBS301

This project involves analyzing Facebook comments from the Washington Post, NYT, or SMH using an Excel spreadsheet and SPSS. The student selected and collected at least 200 comments (or 100 for external students) from various posts. These comments were then coded based on a provided coding scheme, assessing clarity of ideas, level of emotion, objectivity, and perspectives (past and now) on a scale of 1 to 7. The coded data was entered into an Excel file, which serves as the primary dataset. The project then utilizes SPSS to perform cluster analysis on the coded data, aiming to identify different segments within the Facebook comments based on the coded variables. The final report includes the project's objectives, methodology, limitations, identified segments, and recommendations for products and services tailored to each segment, accompanied by appendices that contain SPSS cluster outputs, the Excel data file with coded comments, and the downloaded Facebook comments.

Your temporary usage period for IBM SPSS Statistics will expire in 14 days.
NEW FILE.
DATASET NAME DataSet1 WINDOW=FRONT.
GET DATA /TYPE=XLSX
/FILE='C:\Users\Me\Desktop\Tax Post.xlsx'
/SHEET=name 'Sheet1'
/CELLRANGE=full
/READNAMES=on
/ASSUMEDSTRWIDTH=32767.
EXECUTE.
DATASET NAME DataSet2 WINDOW=FRONT.
CLUSTER ClarityofIdeas Levelofemotion PastPerspective NowPerspective
/METHOD BAVERAGE
/MEASURE=PH2
/PRINT SCHEDULE
/PLOT DENDROGRAM VICICLE.
Cluster
Notes
Output Created 24-Oct-2018 00:02:47
Comments
Input Active Dataset DataSet2
Filter <none>
Weight <none>
Split File <none>
N of Rows in Working Data
File
200
Missing Value Handling Definition of Missing User-defined missing values are treated
as missing.
Cases Used Statistics are based on cases with no
missing values for any variable used.

Syntax CLUSTER ClarityofIdeas
Levelofemotion PastPerspective
NowPerspective
/METHOD BAVERAGE
/MEASURE=PH2
/PRINT SCHEDULE
/PLOT DENDROGRAM VICICLE.
Resources Processor Time 00 00:00:01.170
Elapsed Time 00 00:00:02.183
[DataSet2]
Case Processing Summarya,b
Cases
Valid
Rejected
TotalMissing Value Negative Value
N Percent N Percent N Percent N Percent
200 100.0 0 .0 0 .0 200 100.0
a. Phi-square between Sets of Frequencies used
b. Average Linkage (Between Groups)
Average Linkage (Between Groups)
Agglomeration Schedule
Stage
Cluster Combined
Coefficients
Stage Cluster First Appears
Next StageCluster 1 Cluster 2 Cluster 1 Cluster 2
1 117 200 .000 0 0 84
2 169 199 .000 0 0 32
3 77 198 .000 0 0 150

4 185 197 .000 0 0 16
5 187 196 .000 0 0 14
6 183 195 .000 0 0 18
7 182 194 .000 0 0 19
8 181 193 .000 0 0 20
9 180 192 .000 0 0 21
10 179 191 .000 0 0 22
11 178 190 .000 0 0 23
12 177 189 .000 0 0 24
13 176 188 .000 0 0 25
14 2 187 .000 0 5 29
15 111 186 .000 0 0 90
16 17 185 .000 0 4 80
17 172 184 .000 0 0 29
18 15 183 .000 0 6 93
19 14 182 .000 0 7 120
20 13 181 .000 0 8 95
21 12 180 .000 0 9 96
22 11 179 .000 0 10 97
23 10 178 .000 0 11 77
24 9 177 .000 0 12 99
25 8 176 .000 0 13 100
26 124 175 .000 0 0 77
27 102 174 .000 0 0 99
28 101 173 .000 0 0 100
29 2 172 .000 14 17 101
30 159 171 .000 0 0 42
31 98 170 .000 0 0 185
32 51 169 .000 0 2 57
33 161 168 .000 0 0 40
34 164 167 .000 0 0 37
35 149 166 .000 0 0 52
36 93 165 .000 0 0 148
37 60 164 .000 0 34 105
38 144 163 .000 0 0 57
39 148 162 .000 0 0 53
40 89 161 .000 0 33 104
41 88 160 .000 0 0 146
42 39 159 .000 0 30 69
43 86 158 .000 0 0 167

44 64 157 .000 0 0 159
45 83 156 .000 0 0 112
46 132 155 .000 0 0 69
47 61 154 .000 0 0 142
48 95 153 .000 0 0 105
49 80 152 .000 0 0 114
50 58 151 .000 0 0 151
51 127 150 .000 0 0 74
52 1 149 .000 0 35 124
53 30 148 .000 0 39 70
54 119 147 .000 0 0 82
55 53 146 .000 0 0 144
56 52 145 .000 0 0 176
57 51 144 .000 32 38 108
58 121 143 .000 0 0 80
59 131 142 .000 0 0 70
60 135 141 .000 0 0 66
61 47 140 .000 0 0 154
62 136 139 .000 0 0 65
63 126 138 .000 0 0 75
64 44 137 .000 0 0 153
65 43 136 .000 0 62 130
66 42 135 .000 0 60 129
67 41 134 .000 0 0 132
68 40 133 .000 0 0 173
69 39 132 .000 42 46 110
70 30 131 .000 53 59 109
71 105 130 .000 0 0 96
72 36 129 .000 0 0 181
73 35 128 .000 0 0 153
74 34 127 .000 0 51 121
75 33 126 .000 0 63 131
76 32 125 .000 0 0 177
77 10 124 .000 23 26 135
78 90 123 .000 0 0 109
79 29 122 .000 0 0 156
80 17 121 .000 16 58 127
81 27 120 .000 0 0 147
82 26 119 .000 0 54 126
83 112 118 .000 0 0 89

84 24 117 .000 0 1 115
85 23 116 .000 0 0 172
86 22 115 .000 0 0 155
87 21 114 .000 0 0 154
88 20 113 .000 0 0 179
89 19 112 .000 0 83 137
90 18 111 .000 0 15 162
91 50 110 .000 0 0 127
92 100 109 .000 0 0 101
93 15 108 .000 18 0 190
94 72 107 .000 0 0 120
95 13 106 .000 20 0 140
96 12 105 .000 21 71 134
97 11 104 .000 22 0 145
98 31 103 .000 0 0 135
99 9 102 .000 24 27 177
100 8 101 .000 25 28 157
101 2 100 .000 29 92 138
102 87 99 .000 0 0 110
103 91 97 .000 0 0 108
104 89 96 .000 40 0 148
105 60 95 .000 37 48 107
106 56 94 .000 0 0 124
107 60 92 .000 105 0 174
108 51 91 .000 57 103 119
109 30 90 .000 70 78 128
110 39 87 .000 69 102 122
111 81 85 .000 0 0 166
112 63 83 .000 0 45 118
113 71 82 .000 0 0 176
114 59 80 .000 0 49 171
115 24 79 .000 84 0 141
116 73 78 .000 0 0 119
117 66 75 .000 0 0 121
118 63 74 .000 112 0 143
119 51 73 .000 108 116 156
120 14 72 .000 19 94 158
121 34 66 .000 74 117 123
122 39 62 .000 110 0 166
123 34 57 .000 121 0 167

124 1 56 .000 52 106 159
125 49 55 .000 0 0 128
126 26 54 .000 82 0 164
127 17 50 .000 80 91 136
128 30 49 .000 109 125 133
129 42 48 .000 66 0 147
130 43 46 .000 65 0 149
131 33 45 .000 75 0 145
132 4 41 .000 0 67 158
133 30 38 .000 128 0 150
134 12 37 .000 96 0 182
135 10 31 .000 77 98 162
136 17 28 .000 127 0 149
137 19 25 .000 89 0 144
138 2 16 .000 101 0 157
139 65 69 .033 0 0 146
140 13 70 .034 95 0 151
141 24 76 .035 115 0 170
142 5 61 .035 0 47 152
143 63 67 .036 118 0 152
144 19 53 .037 137 55 155
145 11 33 .037 97 131 161
146 65 88 .037 139 41 169
147 27 42 .038 81 129 165
148 89 93 .039 104 36 164
149 17 43 .039 136 130 170
150 30 77 .042 133 3 163
151 13 58 .042 140 50 160
152 5 63 .043 142 143 163
153 35 44 .044 73 64 168
154 21 47 .046 87 61 186
155 19 22 .046 144 86 168
156 29 51 .049 79 119 165
157 2 8 .049 138 100 178
158 4 14 .051 132 120 178
159 1 64 .054 124 44 169
160 7 13 .056 0 151 161
161 7 11 .057 160 145 183
162 10 18 .061 135 90 180
163 5 30 .061 152 150 175

164 26 89 .061 126 148 171
165 27 29 .062 147 156 175
166 39 81 .063 122 111 185
167 34 86 .064 123 43 188
168 19 35 .065 155 153 179
169 1 65 .065 159 146 174
170 17 24 .065 149 141 172
171 26 59 .067 164 114 189
172 17 23 .069 170 85 181
173 3 40 .071 0 68 182
174 1 60 .072 169 107 189
175 5 27 .073 163 165 187
176 52 71 .080 56 113 190
177 9 32 .082 99 76 180
178 2 4 .082 157 158 183
179 19 20 .086 168 88 187
180 9 10 .094 177 162 192
181 17 36 .095 172 72 184
182 3 12 .096 173 134 193
183 2 7 .096 178 161 191
184 17 68 .100 181 0 192
185 39 98 .106 166 31 188
186 21 84 .108 154 0 198
187 5 19 .111 175 179 191
188 34 39 .111 167 185 195
189 1 26 .127 174 171 193
190 15 52 .129 93 176 194
191 2 5 .134 183 187 194
192 9 17 .135 180 184 196
193 1 3 .136 189 182 195
194 2 15 .176 191 190 197
195 1 34 .188 193 188 199
196 6 9 .195 0 192 197
197 2 6 .202 194 196 198
198 2 21 .236 197 186 199
199 1 2 .241 195 198 0

CLUSTER ClarityofIdeas Levelofemotion PastPerspective NowPerspective
levelofobjectivity FuturePerspective Levelfocusonpersonalities
LevelofCriticismofcorporatebusiness
Levelofcriticismofthegovernmentpublicservicedepartments
/METHOD BAVERAGE
/MEASURE=PH2
/PRINT SCHEDULE
/PLOT DENDROGRAM VICICLE.
Cluster
Notes
Output Created 24-Oct-2018 00:14:43
Comments
Input Active Dataset DataSet2
Filter <none>
Weight <none>
Split File <none>
N of Rows in Working Data
File
200
Missing Value Handling Definition of Missing User-defined missing values are treated
as missing.
Cases Used Statistics are based on cases with no
missing values for any variable used.

Syntax CLUSTER ClarityofIdeas
Levelofemotion PastPerspective
NowPerspective levelofobjectivity
FuturePerspective
Levelfocusonpersonalities
LevelofCriticismofcorporatebusiness
Levelofcriticismofthegovernmentpublics
ervicedepartments
/METHOD BAVERAGE
/MEASURE=PH2
/PRINT SCHEDULE
/PLOT DENDROGRAM VICICLE.
Resources Processor Time 00 00:00:00.655
Elapsed Time 00 00:00:00.656
[DataSet2]
Case Processing Summarya,b
Cases
Valid
Rejected
TotalMissing Value Negative Value
N Percent N Percent N Percent N Percent
196 98.0 4 2.0 0 .0 200 100.0
a. Phi-square between Sets of Frequencies used
b. Average Linkage (Between Groups)
Average Linkage (Between Groups)
Agglomeration Schedule

Stage
Cluster Combined
Coefficients
Stage Cluster First Appears
Next StageCluster 1 Cluster 2 Cluster 1 Cluster 2
1 79 200 .000 0 0 106
2 78 199 .000 0 0 182
3 77 198 .000 0 0 119
4 185 197 .000 0 0 16
5 184 196 .000 0 0 17
6 183 195 .000 0 0 18
7 182 194 .000 0 0 19
8 181 193 .000 0 0 20
9 180 192 .000 0 0 21
10 179 191 .000 0 0 22
11 178 190 .000 0 0 23
12 177 189 .000 0 0 24
13 176 188 .000 0 0 25
14 172 187 .000 0 0 29
15 111 186 .000 0 0 88
16 17 185 .000 0 4 89
17 16 184 .000 0 5 90
18 15 183 .000 0 6 91
19 14 182 .000 0 7 92
20 13 181 .000 0 8 93
21 12 180 .000 0 9 94
22 11 179 .000 0 10 95
23 10 178 .000 0 11 96
24 9 177 .000 0 12 97
25 8 176 .000 0 13 98
26 103 175 .000 0 0 96
27 102 174 .000 0 0 97
28 101 173 .000 0 0 98
29 100 172 .000 0 14 161
30 99 171 .000 0 0 120
31 98 170 .000 0 0 136
32 97 169 .000 0 0 99
33 96 168 .000 0 0 167
34 95 167 .000 0 0 130
35 94 166 .000 0 0 130
36 93 165 .000 0 0 111
37 92 164 .000 0 0 124
38 91 163 .000 0 0 99