0. Introduction
The August issue of "Public Relations Yokohama" was posted, so read it immediately. I always enjoyed reading it because I was always referred to by household consultations, such as "Well, the monthly food expenses for two people were too high for 50,000 yen !?" This month, there was an article about Yokohama City IR pub rice (I was doing it around April of this year), so when I looked at it, I heard that about 10,000 pub rice were received. It is unlikely that pub rice will receive such comments, so
I wondered if there was any raw data, and when I looked at it it was!
The raw text data was released after processing information such as slander and slander.
The city of Yokohama categorized the issues of pub rice into about five,
- I think there are more issues,
- What kind of opinion was reflected in the "Yokohama IR (Integrated Resort) Direction (Draft)" revised based on pub rice?
I thought, so I decided to do a basic analysis for the time being.
1. Aggregation results described in the pub rice summary report
For the time being, you can see the overall result.
1.1 Number of submitters of opinions
- 5,040 people / organizations submit 9,509 opinions
Submission method |
Number of submitters of opinions |
Mail |
1782 |
F A X |
1189 |
e-mail |
1724 |
Bring a window |
345 |
total |
5040 |
1.2 Classification of opinions
category |
Opinion item |
Number of opinions |
|
Opinion on direction (draft)- |
8621 cases |
3.1 |
Yokohama IR Direction Basic Concept-Yokohama IR Direction Basic Concept |
(995 cases) |
3.2 |
Yokohama IR Direction 1 Achieve the world's highest level of IR-Yokohama IR Direction 1 Achieve the world's highest level of IR |
(877 cases) |
3.3 |
Direction of Yokohama IR 2 Fusion with the city center coastal area-Direction of Yokohama IR 2 Fusion with the city center coastal area |
(789 cases) |
3.4 |
Yokohama IR Direction 3 Innovation in tourism and economy at All Yokohama-Yokohama IR Direction 3 Innovation in tourism and economy at All Yokohama |
(1620 cases) |
3.5 |
Direction of Yokohama IR 4 Construction of Yokohama model for safety and security measures-Direction of Yokohama IR 4 Construction of Yokohama model for safety and security measures |
(1366 cases) |
3.6 |
Background of efforts, effect of IR realization, promotion of understanding of the region, consensus building, schedule, etc.-Background of efforts, effect of IR realization, promotion of understanding of the region, consensus building, schedule, etc. |
(2974 cases) |
4 |
Other opinions (opinions not related to the draft)- |
888 cases |
|
total- |
9509 cases |
1.3 Status of response to opinions
Classification |
Correspondence situation |
Number of opinions |
Repair |
What will be used as a reference for changing the draft |
387 cases |
Consideration |
Items already described in the draft, items that will be used as a reference for future projects and initiatives |
8234 cases |
Other |
Other opinions (opinions not related to the draft) |
888 cases |
total |
|
9509 cases |
2 Take a look
-
Read data (Data is extracted from the above report and sent to tsv)
It was a little difficult to extract from the pdf data, but the following processed data.
-
In addition, [Publish as tsv file on google spread sheet](https://docs.google.com/spreadsheets/d/e/2PACX-1vSzhD4TYx7nQ1a73zQW6ufe9w9-jEuwgYcwPLeM-ey25XbSTwYQUkw8802UM2DMLzpnS92vhn If you want to analyze it yourself, but the processing is troublesome, please.
Is it okay if pub rice corresponds to when copyright is restricted? ?? ??
df = pd.read_csv("https://docs.google.com/spreadsheets/d/e/2PACX-1vSzhD4TYx7nQ1a73zQW6ufe9w9-jEuwgYcwPLeM-ey25XbSTwYQUkw8802UM2DMLzpnS92vHn8jQdkj/pub?gid=1919825840&single=true&output=tsv",sep='\t')
2.1 Word aggregation
Aggregate only nouns. It seems that what you are saying is quite transmitted.
2.1.1 (Miscellaneous) Pros and cons
If the word "agree / disagree" is included, a line of pros and cons will be created because it will be for / disagree with this proposal.
df ['sanpi'] = df ['opinion']. Apply (lambda x:'agree' if'agree' in x or'agree' in x
else ('opposite' if'opposite' in x or'withdraw' in x
else'unprocessed')))
df['sanpi'].value_counts()
result
It's quite divided. Since there is a mixture of pros and cons for unprocessed, processing is required.
position |
number |
Untreated |
6404 |
Opposition |
2106 |
Agree |
1002 |
for pos in ['Agree',' Disagree','Unprocessed']:
print ("---- {} Opinion ----". format (pos))
print (df [df ['sanpi'] == pos] ['opinion']. Head (5))
---- Agree ----
1 I agree with you. Please proceed positively. By the way, I was born and raised in Yokohama. When I was little, Yamashita Park was ...
4 I agree with IR I think Yokohama will be better. I will do my best to support you! !!
5 I agree with IR. I think Yokohama will be better. good luck! !!
6 I agree with IR. I think this is a great opportunity to utilize the potential of Yokohama. I support you! !!
8 I agree with IR. I want Yokohama to be 100 years old and say "I'm glad I lived in Yokohama all the time" ...
Name: Opinion, dtype: object
----opposite opinion----
2 Absolutely the opposite.
3 The introduction of IR attraction should be withdrawn immediately.
7 I am against attracting IRs. I don't think it is necessary in Japan, of course, in Yokohama.
11 The draft direction of Yokohama IR states that it is beautiful, but the biggest Nerai is to build a casino facility in it ...
12 Absolutely no questions asked No casino required
Name: Opinion, dtype: object
---- Unprocessed Opinion ----
0 We should proceed for the future of Yokohama.
18 With the consumption of Japan as a whole declining in Corona and the economy stagnating, the mayor is encouraged to finance from Yokohama at IR Casino ...
23 The spread of the new coronavirus is having a major impact on the world economy. Even in Japan ...
25 I AGREE TO INVITING YOKOHAMA IR!! YOKOHAMA IR ...
26 I think it's very good
2.2 Word cloud
2.2.1 Overall
2.2.2 By "correction" and "reference"
I thought the topic had changed drastically, but it didn't change much at first glance. ..
2.3 Characteristic word group for each category
2.3.1 Differentiation of "opinion" and "correction"
Calculate the importance by creating 5 models centered on the wood system, which are classified by 2 values, whether they end with "reference" or are reflected up to "correction". The closer it is to yellow, the higher the importance (words that appear biased toward either side). This one seems to better see the topics reflected in the "correction" opinion.
A confusion matrix is created and the F value is about 0.96.
It seems that the fact that the number of data is unbalanced but can be divided cleanly reflects a specific opinion. This time around, the economic effect on the "shopping" district, measures against "infectious diseases", and "over tourism". Is "code" a dress code?
- With validation data
[[ 84 14]
[ 0 2058]]
0.9598435462842242
Let's look at some specific comments from the most important ones.
- Pub rice related to "shops"
word ='shop'
df [df ['opinion'] .str.contains (word)]
- "Infection" related pub rice
word ='infection'
df [df ['opinion'] .str.contains (word)]
- Pub rice related to "over tourism"
I heard this word for the first time.
word ='overtourism'
df [df ['opinion'] .str.contains (word)]
|
category |
No |
opinion |
Correspondence situation |
1534 |
3.2 |
540.0 |
I want you to improve the surrounding environment at the same time so as not to become overtourism. |
Fix |
1539 |
3.2 |
545.0 |
Due to the problem of coronavirus infection, it became clear that excessive human concentration should be avoided.... |
Fix |
1542 |
3.2 |
548.0 |
Develop roads, pedestrian walkways, and public transportation that can accommodate large-scale customer attraction facilities, and deal with traffic congestion and overtourism... |
Fix |
1546 |
3.2 |
552.0 |
It is a draft with 20 to 40 million visitors, and I do not know if I expect this, but Nishi Ward and... |
Fix |
1547 |
3.2 |
553.0 |
The current city of Yokohama is already overpopulated, and if more people come, the surrounding area will become over-tourist.... |
Fix |
1549 |
3.2 |
555.0 |
I would like you to take measures such as security, addiction, and overtourism to revitalize Yokohama. |
Fix |
2605 |
3.3 |
732.0 |
Regarding access to the area around IR, it may be insufficient for articulated buses. Singapore... |
reference |
2.3.2 Distinguishing between "agree" and "disagree"
- Calculate the importance of words that often appear (do not appear) in "agree" or "disagree". I can't paste the image, so markdown. ..
Writing "casino" is the opposite, and writing IR seems to be in favor.
|
features |
Random Forest feature importances |
Extra Trees feature importances |
AdaBoost feature importances |
Gradient Boost feature importances |
SVC featrure importances |
1285 |
casino |
0.045144 |
0.015389 |
0.013333 |
0.219394 |
0.045144 |
6946 |
IR |
0.031946 |
0.009200 |
0.006667 |
0.050034 |
0.031946 |
5602 |
Absolutely |
0.029189 |
0.014611 |
0.010000 |
0.044003 |
0.029189 |
3867 |
Thoughts |
0.018031 |
0.009544 |
0.006667 |
0.028076 |
0.018031 |
944 |
want |
0.027549 |
0.011890 |
0.003333 |
0.026869 |
0.027549 |
979 |
No |
0.011003 |
0.003524 |
0.006667 |
0.024061 |
0.011003 |
3629 |
Citizen |
0.003703 |
0.001643 |
0.006667 |
0.014392 |
0.003703 |
661 |
Can |
0.002244 |
0.002126 |
0.013333 |
0.013667 |
0.002244 |
740 |
Absent |
0.006860 |
0.001467 |
0.006667 |
0.013362 |
0.006860 |
70 |
Good |
0.024577 |
0.013051 |
0.010000 |
0.013212 |
0.024577 |
662 |
it can |
0.017260 |
0.004285 |
0.006667 |
0.012382 |
0.017260 |
325 |
Please give me |
0.010329 |
0.007631 |
0.010000 |
0.011040 |
0.010329 |
3877 |
think |
0.011447 |
0.007665 |
0.006667 |
0.011004 |
0.011447 |
4893 |
Activity |
0.011980 |
0.033780 |
0.003333 |
0.010879 |
0.011980 |
667 |
is |
0.007067 |
0.003214 |
0.003333 |
0.010223 |
0.007067 |
6064 |
plan |
0.010016 |
0.002721 |
0.006667 |
0.009909 |
0.010016 |
433 |
Tightly |
0.005392 |
0.016280 |
0.003333 |
0.009701 |
0.005392 |
3974 |
opinion |
0.005566 |
0.001066 |
0.003333 |
0.009596 |
0.005566 |
812 |
about |
0.007158 |
0.006062 |
0.013333 |
0.009207 |
0.007158 |
364 |
thing |
0.002742 |
0.000340 |
0.003333 |
0.009126 |
0.002742 |
366 |
this |
0.001693 |
0.000244 |
0.003333 |
0.007973 |
0.001693 |
4402 |
Measures |
0.006044 |
0.010119 |
0.010000 |
0.007203 |
0.006044 |
5237 |
development |
0.013451 |
0.008657 |
0.003333 |
0.006650 |
0.013451 |
5254 |
Blank paper |
0.001903 |
0.002185 |
0.003333 |
0.006503 |
0.001903 |
6292 |
Gambling |
0.013954 |
0.003473 |
0.010000 |
0.006346 |
0.013954 |
2306 |
Dependence |
0.011650 |
0.003975 |
0.003333 |
0.006191 |
0.011650 |
134 |
Is |
0.005019 |
0.001538 |
0.006667 |
0.005584 |
0.005019 |
6019 |
Tourism |
0.006276 |
0.005610 |
0.003333 |
0.005410 |
0.006276 |
2214 |
However, |
0.000887 |
0.000535 |
0.003333 |
0.005279 |
0.000887 |
3162 |
Basic |
0.005198 |
0.003290 |
0.010000 |
0.005259 |
0.005198 |
273 |
Can be |
0.001151 |
0.001321 |
0.003333 |
0.004983 |
0.001151 |
4427 |
quickly |
0.002175 |
0.005300 |
0.003333 |
0.004890 |
0.002175 |
4249 |
Promotion |
0.001771 |
0.000212 |
0.000000 |
0.004880 |
0.001771 |
5551 |
Draft |
0.001307 |
0.002154 |
0.003333 |
0.004786 |
0.001307 |
975 |
Masu |
0.007489 |
0.000759 |
0.000000 |
0.004608 |
0.007489 |
4547 |
Expectations |
0.011055 |
0.012767 |
0.006667 |
0.004488 |
0.011055 |
778 |
If |
0.001325 |
0.000296 |
0.003333 |
0.004451 |
0.001325 |
2137 |
How it works |
0.007645 |
0.012704 |
0.006667 |
0.004389 |
0.007645 |
1324 |
gambling |
0.009497 |
0.004378 |
0.006667 |
0.004227 |
0.009497 |
2119 |
this time |
0.003435 |
0.002226 |
0.003333 |
0.003688 |
0.003435 |
2546 |
Can do |
0.005972 |
0.006023 |
0.006667 |
0.003683 |
0.005972 |
4688 |
Yokohama |
0.002548 |
0.001370 |
0.000000 |
0.003650 |
0.002548 |
480 |
To do |
0.002029 |
0.001075 |
0.003333 |
0.003648 |
0.002029 |
5879 |
Go |
0.001787 |
0.002110 |
0.003333 |
0.003633 |
0.001787 |
4452 |
I'd love to |
0.002008 |
0.003961 |
0.006667 |
0.003410 |
0.002008 |
2980 |
Included |
0.000075 |
0.000032 |
0.006667 |
0.003407 |
0.000075 |
787 |
Become |
0.001587 |
0.000883 |
0.006667 |
0.003274 |
0.001587 |
2445 |
Admission |
0.001122 |
0.000649 |
0.003333 |
0.003221 |
0.001122 |
1600 |
Pachislot |
0.000000 |
0.000612 |
0.003333 |
0.002849 |
0.000000 |
278 |
From |
0.001011 |
0.000759 |
0.000000 |
0.002804 |
0.001011 |
-
1 Confusion matrix with validation data
[[513 4]
[ 17 243]]
0.9692612875332733
-
2 Please note that the judgment will be incorrect unless the words "agree", "disagree", etc.) that are the basis of the classification are excluded.
df ['wakati'] = df ['opinion'] .apply (wakati_mecab)
df['wakati'] = df['wakati'].replace({'Agree|Agree|Opposition|Withdrawal':''},regex=True)
matrix, names, y_tra = get_sparce_matrix (df [df ['sanpi']! ='Unprocessed'],'wakati','sanpi')
2.4 LDA (topic model)
- What topics are there in {Agree-Disagree / Each category}?
Agree summary>
====== Topic 0 ======
word prob
0 gold 0.039881
1 Agree 0.019905
2 IR 0.019235
3 years 0.012214
4 early 0.010971
5 Hope 0.010420
6 cities 0.010050
7 Yokohama 0.009538
8 Citizen 0.009480
9 Burden 0.008753
====== Topic 1 ======
word prob
0 Agree 0.036193
1 IR 0.032817
2 people 0.026546
3 thought 0.025401
4 Yokohama 0.024380
5 target 0.021133
6 Corona 0.017271
7 Introduction 0.016123
8 Casino 0.012665
9 Specific 0.012142
====== Topic 2 ======
word prob
0 nan 0.062391
1 year 0.038379
2 Agree 0.019877
Episode 3 0.017015
4 method 0.016732
5 Sales increase 0.016436
6 Election 0.015749
7 IR 0.015739
8 1 0.011609
9 reduction 0.011422
====== Topic 3 ======
word prob
0 Agree 0.025471
1 IR 0.024914
2 Municipal administration 0.019222
3 Citizens 0.019068
4 selections 0.016680
5 Yokohama 0.014022
6 mayor 0.012883
7 Impact 0.011415
8 city 0.010853
9 town 0.010783
====== Topic 4 ======
word prob
0 Yokohama 0.047014
1 IR 0.039254
2 mayor 0.024489
3 Agree 0.024379
4 ・ 0.0188898
5 Attract 0.017829
6 Promotion 0.015244
7 cities 0.014124
8 Many 0.013337
9 hearing 0.012633
====== Topic 5 ======
word prob
0 Citizen 0.056743
1 IR 0.040896
2 Casino 0.038895
3 Yokohama 0.037232
4 Agree 0.036916
5 Opposition 0.023289
6 mayor 0.023218
7 Attract 0.018109
8 Description 0.016881
9 thought 0.016789
====== Topic 6 ======
word prob
0 nan 0.938510
1 Reflected 0.001564
2 Positive 0.001365
3 Trust 0.001182
4 Procedure 0.001160
5 IR 0.000941
6 times 0.000897
7 thought 0.000773
8 launch 0.000688
9 Agree 0.000584
====== Topic 7 ======
word prob
0 nan 0.082423
1 Q 0.022329
2 mayor 0.021095
3 Agree 0.020343
4 Result 0.017322
5 Yokohama 0.016735
6 factions 0.015124
7 HP 0.014980
8 IR 0.013357
9 Casino 0.012042
====== Topic 8 ======
word prob
0 IR 0.057196
1 Yokohama 0.039346
2 Agree 0.034646
3 thought 0.034076
4 Residents 0.029105
5 votes 0.026869
6 Attract 0.023697
7 people 0.015772
8 cities 0.012917
9 Business 0.012631
====== Topic 9 ======
word prob
0 0 0.042875
1 Casino 0.035204
2 2 0.021080
3 o'clock 0.016271
4 gambling 0.015599
5 Opposition 0.013966
6 9 0.012230
7 Plan 0.011809
8 nan 0.011778
9 ) 0.011564
Opposite summary>
====== Topic 0 ======
word prob
0 IR 0.034444
1 Casino 0.031587
2 Yokohama 0.028335
3 Opposite 0.025735
4 cities 0.019126
5 Citizen 0.017848
6 2 0.016689
7 0 0.015812
8 sex 0.014714
9 ) 0.013129
====== Topic 1 ======
word prob
0 Casino 0.099108
1 Opposite 0.073668
2 Yokohama 0.056968
3 IR 0.036165
4 Absolute 0.033869
5 Attract 0.031747
6 cities 0.021524
7 Finance 0.016254
8 gambling 0.012545
9 Gambling 0.011134
====== Topic 2 ======
word prob
0 Casino 0.039083
1 Opposite 0.025963
2 illness 0.025086
3 dependence 0.022148
4 people 0.020454
5 Opinion 0.019148
6 Attract 0.019066
7 Citizens 0.018166
8 many 0.017188
9 IR 0.016424
====== Topic 3 ======
word prob
0 Corona 0.042335
1 Casino 0.030375
2 Opposite 0.021179
3 New 0.019993
4 infection 0.018356
5 messenger 0.017009
6 Tax 0.015720
7 Yokohama 0.015411
8 Budget 0.014799
9 virus 0.012776
====== Topic 4 ======
word prob
0 Blank paper 0.093806
1 year 0.051971
2 0 0.025658
3 Citizen 0.021323
After 4 0.020978
5 Decision 0.020293
6 ) 0.020253
7 ( 0.020068
8 election 0.019678
9 Opposition 0.018437
====== Topic 5 ======
word prob
0 Citizen 0.028442
1 Last year 0.018782
2 Opinion 0.018358
3 Yokohama 0.015966
4 Policy 0.015784
5 Gambling 0.012446
6 ears 0.012267
7 heads 0.010973
8 words 0.010696
9 town 0.009997
====== Topic 6 ======
word prob
0 Casino 0.040258
1 mayor 0.038348
2 Citizen 0.030434
3 IR 0.029625
4 Yokohama 0.026991
5 Opposition 0.026174
6 Attract 0.022058
7 cities 0.019688
8 ? 0.015200
9 Residents 0.014024
====== Topic 7 ======
word prob
0 nan 0.923342
1 own 0.002323
2 young 0.001715
3 avoidance 0.001700
4 times 0.001219
5 Junior high school 0.001190
6 flow 0.001123
7 December 0.000912
8 special 0.000902
9 Parent 0.000882
====== Topic 8 ======
word prob
0 opposite 0.062047
1 ! 0.042702
2 Citizen 0.037311
3 mayor 0.035762
4 Casino 0.032417
5 IR 0.028107
6 votes 0.019678
7 Opinion 0.018379
8 Yokohama 0.018074
9 misfortune 0.015743
====== Topic 9 ======
word prob
0 Casino 0.052197
1 Citizen 0.036918
2 Yokohama 0.033726
3 Opposite 0.030859
4 ・ 0.020238
5 ! 0.015056
6 people 0.014770
7 IR 0.013741
8 thought 0.013240
9 Promise 0.012745
3.1 Yokohama IR Direction Basic Concept-Yokohama IR Direction Basic Concept summary>
====== Topic 0 ======
word prob
0 Yokohama 0.046032
1 IR 0.036601
2 cities 0.017276
3 Casino 0.016841
4 Agree 0.015108
5 Thoughts 0.012211
6 Citizen 0.010738
7 Attract 0.009912
8 ! 0.009425
9 ) 0.008918
====== Topic 1 ======
word prob
0 IR 0.051729
1 Opposite 0.034088
2 Agree 0.024974
3 Yokohama 0.020797
4 Attract 0.008087
5 Casino 0.008020
6 below 0.007332
7 comfort 0.005999
8 ( 0.005113
9 Absolute 0.004990
====== Topic 2 ======
word prob
0 nan 0.074913
1 Casino 0.029202
2 IR 0.025825
3 Yokohama 0.021842
4 Attract 0.019968
5 Opposition 0.016199
6 Agree 0.010771
7 ・ 0.007450
8 target 0.006038
9 Consideration 0.005303
====== Topic 3 ======
word prob
0 Yokohama 0.037075
1 IR 0.027041
2 thought 0.021906
3 Japan 0.012058
4 cities 0.009663
5 Economy 0.008272
6 Opposition 0.008173
7 Casino 0.007492
8 Agree 0.007481
9 ・ 0.006800
====== Topic 4 ======
word prob
0 nan 0.048355
1 IR 0.044372
2 Yokohama 0.022841
3 Opposite 0.019988
4 Casino 0.016277
5 Absolute 0.009915
6 thought 0.007707
7 Attract 0.007260
8 Agree 0.007079
9 Need 0.006558
====== Topic 5 ======
word prob
0 ! 0.007202
1 IR 0.006455
2 thought 0.003545
3 good 0.003545
4 YOKOHAMA 0.003297
5 below 0.002565
6 Realization 0.002564
7-ary 0.002564
8 lines 0.002564
9 Anxiety 0.002564
====== Topic 6 ======
word prob
0 Yokohama 0.017978
1 Casino 0.012114
2 IR 0.011228
3 Opposite 0.009582
4 Expectation 0.006183
5 cities 0.005589
6 Thoughts 0.005371
7 nan 0.005023
8 target 0.004956
9 facilities 0.004569
====== Topic 7 ======
word prob
0 nan 0.970669
1 Yokohama 0.000721
2 IR 0.000410
3 Attract 0.000402
4 Casino 0.000363
5 Opposite 0.000340
Senary 0.000278
7 World 0.000274
8 cities 0.000254
9 target 0.000231
====== Topic 8 ======
word prob
0 Yokohama 0.080760
1 IR 0.055955
2 Opposite 0.054105
3 Casino 0.043317
4 ! 0.027844
5 Absolute 0.011920
6 cities 0.011358
7 Need 0.011018
8 Thoughts 0.008408
9 thought 0.008202
====== Topic 9 ======
word prob
0 Yokohama 0.028519
1 IR 0.027840
2 nan 0.025731
3 Opposite 0.024880
4 Agree 0.022008
5 thought 0.016966
3.2 Yokohama IR Direction 1 Achieving the World's Highest Level IR-Yokohama IR Direction 1 Achieving the World's Highest Level IR summary>
====== Topic 0 ======
word prob
0 Yokohama 0.023476
1 IR 0.023091
2 Casino 0.017672
3 thought 0.015606
4 Tourism 0.012936
5 facilities 0.011887
6 comfort 0.007733
7 Consideration 0.006482
8 Citizen 0.005922
9 Agree 0.005666
====== Topic 1 ======
word prob
0 Casino 0.038360
1 IR 0.027691
2 Yokohama 0.020435
3 facilities 0.016945
4 target 0.006540
5 world 0.006237
6 sex 0.006221
7 Opposition 0.005993
8 without 0.005205
9 Citizen 0.005202
====== Topic 2 ======
word prob
0 nan 0.036855
1 IR 0.010983
2 Yokohama 0.009702
3 facilities 0.008351
4 target 0.005629
5 Tourism 0.005305
6 Casino 0.005213
7 lines 0.005048
8 Japan 0.004708
9 world 0.004565
====== Topic 3 ======
word prob
0 nan 0.944313
1 facility 0.001276
2 target 0.000418
3 works 0.000418
4 thought 0.000375
5 Yokohama 0.000365
6 Casino 0.000355
7 IR 0.000353
8 Japan 0.000341
9 people 0.000290
====== Topic 4 ======
word prob
0 nan 0.057626
1 Casino 0.021631
2 IR 0.019492
3 Agree 0.005443
4 Yokohama 0.005235
5 Attract 0.004294
6 thought 0.004125
7 facilities 0.004100
8 ! 0.003875
9 MICE 0.003873
====== Topic 5 ======
word prob
0 Casino 0.016577
1 IR 0.015906
2 facilities 0.011750
3 Yokohama 0.010143
4 world 0.005033
5 Japan 0.004880
6 target 0.004814
7 Citizen 0.004447
8 Need 0.004329
9 Opposition 0.003897
====== Topic 6 ======
word prob
0 Casino 0.020266
1 Yokohama 0.017726
2 IR 0.013827
3 thought 0.011843
4 Tourism 0.009388
5 nan 0.008068
6 Japan 0.005805
7 ・ 0.005298
8 facilities 0.005093
9 target 0.005009
====== Topic 7 ======
word prob
0 IR 0.024849
1 Casino 0.021311
2 Yokohama 0.019356
3 ( 0.015570
4 ) 0.015333
5 ・ 0.0008508
6 Japan 0.007582
7 facilities 0.006963
8 resort 0.006782
9 places 0.005804
====== Topic 8 ======
word prob
0 IR 0.027895
1 Yokohama 0.026965
2 Casino 0.024761
3 facilities 0.012166
4 thought 0.008396
5 Citizen 0.006775
6 Need 0.006117
7 comfort 0.005871
8 Hotel 0.005715
9 target 0.005371
====== Topic 9 ======
word prob
0 Yokohama 0.021339
1 IR 0.018183
2 thought 0.013644
3 Casino 0.009701
4 comfort 0.008678
5 ( 0.008353
6 ) 0.007714
7 Agree 0.007014
8 facilities 0.006693
9 places 0.006601
3.3 Direction of Yokohama IR 2 Fusion with the city center coastal area-Yokohama IR direction 2 Fusion with the city center coastal area summary>
====== Topic 0 ======
word prob
0 thought 0.031435
1 ( 0.021839
2 ) 0.020260
3 IR 0.019925
4 Maintenance 0.019666
5 Yokohama 0.018728
6 1 0.016400
7 district 0.014276
8 Agree 0.011645
9 Casino 0.011184
====== Topic 1 ======
word prob
0 nan 0.050074
1 Yokohama 0.009658
2 Who 0.009350
3 Yes 0.007193
Type 4 0.007018
5 rise 0.006115
6 modern 0.005036
7 ・ 0.004461
8 Casino 0.004421
9 down 0.003957
====== Topic 2 ======
word prob
0 nan 0.060762
1 Casino 0.000836
2 Residence 0.000836
3 Opposite 0.000836
4 town 0.000836
5 Yokohama 0.000319
6 Ranking 0.000318
7 Ming 0.000318
8 including 0.000318
9 Iku 0.000318
====== Topic 3 ======
word prob
0 Yokohama 0.046595
1 IR 0.027358
2 Casino 0.024009
3 cities 0.017719
4 cities 0.013127
5 Plan 0.012836
6 illness 0.012829
7 0 0.011049
8 ! 0.010750
9 image 0.010594
====== Topic 4 ======
word prob
0 Yokohama 0.064073
1 IR 0.034073
2 facilities 0.026399
3 target 0.019416
4 thought 0.014218
5 sex 0.011987
6 disaster 0.011098
7 New 0.010925
8 Casino 0.010170
9 0.009928
====== Topic 5 ======
word prob
0 Yokohama 0.046118
1 Casino 0.036276
2 Countermeasure 0.029657
3 Transportation 0.020583
4 town 0.020112
5 Yamashita 0.019625
6 ・ 0.0187872
7 target 0.015027
8 Park 0.013543
9 Thoughts 0.011970
====== Topic 6 ======
word prob
0 Yokohama 0.014031
1 IR 0.011430
2 infection 0.009386
3 Landscape 0.008865
4 town 0.008599
5 2 0.007873
6 large 0.007661
7 Corona 0.007150
8 Citizen 0.007062
9 Business 0.006678
====== Topic 7 ======
word prob
0 ・ 0.025136
1 Yokohama 0.017455
2 . 0.016707
3 nan 0.016424
4 Casino 0.013441
5 things 0.012911
6 IR 0.010202
7 Foreign 0.009894
8 0 0.009783
9 o'clock 0.008438
====== Topic 8 ======
word prob
0 nan 0.256493
1 withdrawal 0.008938
2 0.007898 worldwide
3 Property 0.003103
4 Yokohama 0.002693
5 Casino 0.002667
6 Tourism 0.001620
7 decline 0.001521
8 Request 0.001520
9 Attract 0.001358
====== Topic 9 ======
word prob
0 nan 0.967214
1 Casino 0.000121
2 Yokohama 0.000084
3 IR 0.000058
4 image 0.000049
5 culture 0.000048
6 Opposition 0.000038
7 Need 0.000034
8 less 0.000033
9 YOKOHAMA 0.000031
3.4 Direction of Yokohama IR 3 Innovation in tourism and economy in all Yokohama-Direction of Yokohama IR 3 Innovation in tourism and economy in all Yokohama summary>
====== Topic 0 ======
word prob
0 estimate 0.007931
1 myself 0.004272
2 Danger 0.004165
3 Business 0.003610
4 Consideration 0.003213
5 Insurance 0.003038
6 through 0.003037
7 unpaid 0.003037
8 Focus 0.003037
9 National Health Insurance 0.003037
====== Topic 1 ======
word prob
0 nan 0.959033
1 IR 0.000011
2 Yokohama 0.000011
3 Casino 0.000011
4 Appropriation 0.000011
5 Determination 0.000011
6 Half price 0.000011
7 cities 0.000011
8 thought 0.000011
9 Trade fair 0.000011
====== Topic 2 ======
word prob
0 nan 0.055498
1 IR 0.000255
2 Yokohama 0.000255
3 Casino 0.000255
4 Appropriation 0.000255
5 Determination 0.000255
6 Half price 0.000255
7 Trade fair 0.000255
8 cities 0.000255
9 Kansai 0.000255
====== Topic 3 ======
word prob
0 Yokohama 0.030913
1 IR 0.030553
2 Casino 0.024471
3 0 0.017319
4 cities 0.015287
5 thought 0.010196
6 Citizen 0.010158
7 effect 0.009052
8 people 0.008950
9 Economy 0.008827
====== Topic 4 ======
word prob
0 Yokohama 0.031740
1 IR 0.030894
2 Casino 0.028182
3 cities 0.016468
4 0 0.013079
5 Citizens 0.010768
6 thought 0.010232
7 target 0.009626
8 Economy 0.008623
9 people 0.008119
====== Topic 5 ======
word prob
0 Yokohama 0.029495
1 IR 0.022474
2 Agree 0.011760
3 children 0.010785
4 Expectation 0.010526
5 effect 0.010443
6 cities 0.008402
7 Economy 0.008175
8 Casino 0.007801
9 Attract 0.007528
====== Topic 6 ======
word prob
0 nan 0.090475
1 IR 0.000245
2 Yokohama 0.000245
3 Casino 0.000245
4 Appropriation 0.000245
5 Determination 0.000245
6 Half price 0.000245
7 Trade Fair 0.000245
8 Kansai 0.000245
9 Next generation 0.000245
====== Topic 7 ======
word prob
0 nan 0.006866
1 North 0.003863
2 Estimate 0.003765
3 souvenir 0.003765
4 method 0.002076
5 However 0.002076
6 Cooking 0.002076
7 Nationality 0.002071
8 limit 0.002071
9 grip 0.002071
====== Topic 8 ======
word prob
0 nan 0.019196
1 half price 0.002064
2 Wiping 0.002063
3 Negative 0.002063
4 IR 0.000264
5 Yokohama 0.000264
6 Casino 0.000264
7 Appropriation 0.000263
8 Determination 0.000263
9 cities 0.000263
====== Topic 9 ======
word prob
0 nan 0.019504
1 Auxiliary 0.002163
2 valve 0.002163
3 Waste 0.002163
4 Nursery school 0.002163
5 Tsuke 0.002111
6 IR 0.000262
7 Yokohama 0.000262
8 Junior high school 0.000262
9 School lunch 0.000262
3.5 Direction of Yokohama IR 4 Construction of Yokohama model of safety and security measures-Direction of Yokohama IR 4 Construction of Yokohama model of safety and security measures summary>
====== Topic 0 ======
word prob
0 dependency 0.009985
1 Gambling 0.007971
2 illness 0.007080
3 Casino 0.006795
4 nan 0.004834
5th grade 0.004428
6 Countermeasure 0.004139
7 cities 0.004110
8 Yokohama 0.003993
9 increase 0.003906
====== Topic 1 ======
word prob
0 nan 0.707560
1 Casino 0.000087
2 dependence 0.000087
3 illness 0.000087
4 Gambling 0.000087
5 Yokohama 0.000087
6 IR 0.000087
7 Countermeasure 0.000087
8 Opposition 0.000087
9 Security 0.000087
====== Topic 2 ======
word prob
0 nan 0.132564
1 Casino 0.000259
2 dependence 0.000259
3 illness 0.000259
4 Gambling 0.000259
5 Yokohama 0.000259
6 IR 0.000258
7 Countermeasure 0.000258
8 Opposite 0.000258
9 Security 0.000258
====== Topic 3 ======
word prob
0 Casino 0.010663
1 dependence 0.008833
2 illness 0.006815
3 nan 0.005925
4 Gambling 0.004672
5 IR 0.004373
6 Opposite 0.004345
7 Yokohama 0.004340
8 i 0.004283
9 Problem 0.002481
====== Topic 4 ======
word prob
0 Casino 0.038447
1 dependency 0.034758
2 illness 0.030814
3 Gambling 0.022548
4 Yokohama 0.022296
5 IR 0.015999
6 Countermeasure 0.014953
7 Opposite 0.012121
8 people 0.011266
9 thought 0.009036
====== Topic 5 ======
word prob
0 Casino 0.039466
1 dependency 0.035619
2 illness 0.032418
3 Gambling 0.022223
4 Yokohama 0.020578
5 Countermeasure 0.016523
6 IR 0.016454
7 Opposite 0.012131
8 people 0.009611
9 thought 0.009363
====== Topic 6 ======
word prob
0 nan 0.357215
1 Casino 0.000192
2 dependence 0.000192
3 illness 0.000192
4 Gambling 0.000191
5 Yokohama 0.000191
6 IR 0.000191
7 Countermeasure 0.000191
8 Opposite 0.000191
9 Security 0.000191
====== Topic 7 ======
word prob
0 nan 0.186162
1 Casino 0.000243
2 dependence 0.000243
3 illness 0.000243
4 Gambling 0.000243
5 Yokohama 0.000242
6 IR 0.000242
7 Countermeasure 0.000242
8 Opposite 0.000242
9 Security 0.000242
====== Topic 8 ======
word prob
0 Casino 0.037000
1 dependency 0.032611
2 illness 0.029437
3 Gambling 0.021825
4 Yokohama 0.019739
5 Countermeasure 0.016257
6 IR 0.015574
7 Opposite 0.010480
8 people 0.009681
9 thought 0.009634
====== Topic 9 ======
word prob
0 nan 0.956174
1 Casino 0.000013
2 dependence 0.000013
3 illness 0.000013
4 Gambling 0.000013
5 Yokohama 0.000013
6 IR 0.000013
7 Countermeasure 0.000013
8 Opposition 0.000013
9 Security 0.000013
3.6 Background of efforts, effect of IR realization, promotion of regional understanding / consensus building, schedule, etc.-Background of efforts, effect of IR realization, promotion of regional understanding / consensus building, schedule, etc. Summary>
====== Topic 0 ======
word prob
0 sandy beach 0.033390
1 ticket 0.016044
2 operator 0.013330
3 nan 0.011632
4 Return 0.010908
5 fish 0.008180
6 shells 0.008180
7 ◆ 0.006741
8 Invitation 0.006704
9 canoe 0.006653
====== Topic 1 ======
word prob
0 Contract 0.024358
1 virus 0.017025
2 virus 0.010052
3 Act 0.007289
4 bound 0.006873
5 in 0.006862
6 event 0.006587
7 Prohibition 0.006284
8 Rejection 0.006153
9 difficulty 0.005524
====== Topic 2 ======
word prob
0 Casino 0.030689
1 Yokohama 0.027350
2 IR 0.027209
3 Citizens 0.019461
4 cities 0.016959
5 Corona 0.014732
6 Opposite 0.010254
7 Thoughts 0.010221
8 Business 0.009930
9 0.009054
====== Topic 3 ======
word prob
0 Casino 0.046275
1 Yokohama 0.028841
2 IR 0.028204
3 cities 0.019273
4 gambling 0.018259
5 Citizens 0.017483
6 Opposition 0.014544
7 Business 0.011322
8 ) 0.009808
9 ( 0.009805
====== Topic 4 ======
word prob
0 nan 0.716229
1 misfortune 0.000056
2 virus 0.000056
3 sandy beach 0.000056
4 virus 0.000056
5 CSR 0.000056
6 Assumption 0.000056
7 Punishment 0.000056
8 Remains 0.000056
9 Sovereignty 0.000056
====== Topic 5 ======
word prob
0 gold 0.030817
1 contract 0.025485
District 2 0.023621
3 virus 0.012662
4 misfortune 0.011943
5 virus 0.010278
6 IR 0.009862
7 propulsion 0.009245
8 priority 0.007648
9 Penalty 0.007552
====== Topic 6 ======
word prob
0 virus 0.012059
1 virus 0.011974
2 misfortune 0.007783
3 Assumption 0.007014
4 First 0.006987
5 Regular 0.006879
6 in 0.006678
7 Agreement 0.006630
8 Disclosure 0.005964
9 Contract 0.005869
====== Topic 7 ======
word prob
0 nan 0.871513
1 misfortune 0.000025
2 virus 0.000025
3 Sandy beach 0.000025
4 virus 0.000025
5 CSR 0.000025
6 Assumption 0.000025
7 Punishment 0.000025
8 Remains 0.000025
9 Sovereignty 0.000025
====== Topic 8 ======
word prob
0 nan 0.152195
1 misfortune 0.000174
2 virus 0.000171
3 virus 0.000169
4 sandy beach 0.000168
5 CSR 0.000168
6 postponed 0.000168
7 Assumption 0.000168
8 punishment 0.000168
9 Remains 0.000168
====== Topic 9 ======
word prob
0 Yokohama 0.036546
1 Citizen 0.029244
2 Casino 0.026907
3 IR 0.026555
4 cities 0.019777
5 ( 0.013212
6 ) 0.013041
7 Opposition 0.012819
8 Description 0.009755
9 target 0.008527
4 Other opinions (opinions not related to the draft) summary>
====== Topic 0 ======
word prob
0 Citizen 0.034754
1 mayor 0.031555
2 Casino 0.025074
3 Yokohama 0.020426
4 IR 0.016711
5 Attract 0.015037
6 Opinion 0.012715
7 Election 0.011609
8 Blank paper 0.011597
9 votes 0.011080
====== Topic 1 ======
word prob
0 Citizen 0.032818
1 mayor 0.031709
2 Casino 0.026090
3 Yokohama 0.021673
4 IR 0.017723
5 Attract 0.012821
6 votes 0.011204
7 Blank paper 0.011120
8 Opinion 0.011087
9 cities 0.011030
====== Topic 2 ======
word prob
0 Mayor 0.033431
1 Citizen 0.032862
2 Casino 0.024000
3 IR 0.018101
4 Yokohama 0.017661
5 Attract 0.014563
6 Blank paper 0.012731
7 Election 0.011170
8 Opinion 0.010372
9 cities 0.009200
====== Topic 3 ======
word prob
0 Citizen 0.036627
1 mayor 0.029157
2 Casino 0.025975
3 IR 0.019609
4 Yokohama 0.018717
5 Attract 0.015018
6 Opinion 0.012309
7 Blank paper 0.011240
8 votes 0.011196
9 Election 0.010792
====== Topic 4 ======
word prob
0 Mayor 0.028106
1 Citizen 0.024026
2 Casino 0.020297
3 IR 0.018479
4 Yokohama 0.018317
5 Blank paper 0.017392
6 votes 0.016034
7 Residents 0.015913
8 election 0.014335
9 Opinion 0.012537
====== Topic 5 ======
word prob
0 Mayor 0.033718
1 Casino 0.028583
2 Citizen 0.026994
3 IR 0.018146
4 Yokohama 0.017711
5 Residents 0.015480
6 Blank paper 0.014311
7 votes 0.013494
8 Opinion 0.012025
9 Attract 0.011533
====== Topic 6 ======
word prob
0 nan 0.023749
1 mayor 0.015400
2 Yokohama 0.009116
3 Casino 0.008974
4 Attract 0.008030
5 decision 0.007883
6 lines 0.007848
7 selections 0.007811
8 destination 0.007774
9 unnecessary 0.007771
====== Topic 7 ======
word prob
0 nan 0.958089
1 mayor 0.000014
2 Citizen 0.000014
3 Casino 0.000014
4 votes 0.000014
5 Residents 0.000014
6 Blank paper 0.000014
7 IR 0.000014
8 Yokohama 0.000014
9 Opinion 0.000014
====== Topic 8 ======
word prob
0 nan 0.058285
1 mayor 0.000317
2 Citizen 0.000316
3 Casino 0.000314
4 votes 0.000313
5 Residents 0.000312
6 Blank paper 0.000311
7 IR 0.000311
8 Yokohama 0.000311
9 Opinion 0.000310
====== Topic 9 ======
word prob
0 Citizen 0.031133
1 mayor 0.028824
2 Casino 0.026333
3 Yokohama 0.019486
4 Residents 0.016416
5 votes 0.016064
6 Blank paper 0.010445
7 Q 0.010179
8 words 0.009699
9 Attract 0.009617
2.5 Co-occurrence network
Under construction
2.6 Sentence vector generation with transformer
making. If you make a two-dimensional map, you can see a mass of opinions.
3. Any comment
making···