Hugging Face's logo

AIDA-UPM
/
MARTINI_enrich_BERTopic_RadioGenoa

Text Classification
BERTopic
Model card Files
xet
Community
AngelPanizo commited on
Commit
91a343c
·
verified ·
1 Parent(s): e91fb4a

Add BERTopic model

Browse files
Files changed (6) hide show
  1. README.md +73 -0
  2. config.json +16 -0
  3. ctfidf.safetensors +3 -0
  4. ctfidf_config.json +1355 -0
  5. topic_embeddings.safetensors +3 -0
  6. topics.json +301 -0
README.md ADDED
@@ -0,0 +1,73 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+
2
+ ---
3
+ tags:
4
+ - bertopic
5
+ library_name: bertopic
6
+ pipeline_tag: text-classification
7
+ ---
8
+
9
+ # MARTINI_enrich_BERTopic_RadioGenoa
10
+
11
+ This is a [BERTopic](https://github.com/MaartenGr/BERTopic) model.
12
+ BERTopic is a flexible and modular topic modeling framework that allows for the generation of easily interpretable topics from large datasets.
13
+
14
+ ## Usage
15
+
16
+ To use this model, please install BERTopic:
17
+
18
+ ```
19
+ pip install -U bertopic
20
+ ```
21
+
22
+ You can use the model as follows:
23
+
24
+ ```python
25
+ from bertopic import BERTopic
26
+ topic_model = BERTopic.load("AIDA-UPM/MARTINI_enrich_BERTopic_RadioGenoa")
27
+
28
+ topic_model.get_topic_info()
29
+ ```
30
+
31
+ ## Topic overview
32
+
33
+ * Number of topics: 4
34
+ * Number of training documents: 170
35
+
36
+ <details>
37
+ <summary>Click here for an overview of all topics.</summary>
38
+
39
+ | Topic ID | Topic Keywords | Topic Frequency | Label |
40
+ |----------|----------------|-----------------|-------|
41
+ | -1 | lampedusa - traffickers - refugees - pope - hungary | 20 | -1_lampedusa_traffickers_refugees_pope |
42
+ | 0 | jihad - hamas - terrorists - mohammed - brussels | 74 | 0_jihad_hamas_terrorists_mohammed |
43
+ | 1 | lampedusa - invaders - refugees - african - unprecedented | 50 | 1_lampedusa_invaders_refugees_african |
44
+ | 2 | sicilians - african - robbed - rapists - slaps | 26 | 2_sicilians_african_robbed_rapists |
45
+
46
+ </details>
47
+
48
+ ## Training hyperparameters
49
+
50
+ * calculate_probabilities: True
51
+ * language: None
52
+ * low_memory: False
53
+ * min_topic_size: 10
54
+ * n_gram_range: (1, 1)
55
+ * nr_topics: None
56
+ * seed_topic_list: None
57
+ * top_n_words: 10
58
+ * verbose: False
59
+ * zeroshot_min_similarity: 0.7
60
+ * zeroshot_topic_list: None
61
+
62
+ ## Framework versions
63
+
64
+ * Numpy: 1.26.4
65
+ * HDBSCAN: 0.8.40
66
+ * UMAP: 0.5.7
67
+ * Pandas: 2.2.3
68
+ * Scikit-Learn: 1.5.2
69
+ * Sentence-transformers: 3.3.1
70
+ * Transformers: 4.46.3
71
+ * Numba: 0.60.0
72
+ * Plotly: 5.24.1
73
+ * Python: 3.10.12
config.json ADDED
@@ -0,0 +1,16 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "calculate_probabilities": true,
3
+ "language": null,
4
+ "low_memory": false,
5
+ "min_topic_size": 10,
6
+ "n_gram_range": [
7
+ 1,
8
+ 1
9
+ ],
10
+ "nr_topics": null,
11
+ "seed_topic_list": null,
12
+ "top_n_words": 10,
13
+ "verbose": false,
14
+ "zeroshot_min_similarity": 0.7,
15
+ "zeroshot_topic_list": null
16
+ }
ctfidf.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9397fc6db6154c55195fbd2b574b836bb77e03c49af8a6dc6f7e26541a2ffe1d
3
+ size 27364
ctfidf_config.json ADDED
@@ -0,0 +1,1355 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "ctfidf_model": {
3
+ "bm25_weighting": false,
4
+ "reduce_frequent_words": true
5
+ },
6
+ "vectorizer_model": {
7
+ "params": {
8
+ "analyzer": "word",
9
+ "binary": false,
10
+ "decode_error": "strict",
11
+ "encoding": "utf-8",
12
+ "input": "content",
13
+ "lowercase": true,
14
+ "max_df": 0.8,
15
+ "max_features": null,
16
+ "min_df": 1,
17
+ "ngram_range": [
18
+ 1,
19
+ 1
20
+ ],
21
+ "stop_words": [
22
+ "i",
23
+ "me",
24
+ "my",
25
+ "myself",
26
+ "we",
27
+ "our",
28
+ "ours",
29
+ "ourselves",
30
+ "you",
31
+ "you're",
32
+ "you've",
33
+ "you'll",
34
+ "you'd",
35
+ "your",
36
+ "yours",
37
+ "yourself",
38
+ "yourselves",
39
+ "he",
40
+ "him",
41
+ "his",
42
+ "himself",
43
+ "she",
44
+ "she's",
45
+ "her",
46
+ "hers",
47
+ "herself",
48
+ "it",
49
+ "it's",
50
+ "its",
51
+ "itself",
52
+ "they",
53
+ "them",
54
+ "their",
55
+ "theirs",
56
+ "themselves",
57
+ "what",
58
+ "which",
59
+ "who",
60
+ "whom",
61
+ "this",
62
+ "that",
63
+ "that'll",
64
+ "these",
65
+ "those",
66
+ "am",
67
+ "is",
68
+ "are",
69
+ "was",
70
+ "were",
71
+ "be",
72
+ "been",
73
+ "being",
74
+ "have",
75
+ "has",
76
+ "had",
77
+ "having",
78
+ "do",
79
+ "does",
80
+ "did",
81
+ "doing",
82
+ "a",
83
+ "an",
84
+ "the",
85
+ "and",
86
+ "but",
87
+ "if",
88
+ "or",
89
+ "because",
90
+ "as",
91
+ "until",
92
+ "while",
93
+ "of",
94
+ "at",
95
+ "by",
96
+ "for",
97
+ "with",
98
+ "about",
99
+ "against",
100
+ "between",
101
+ "into",
102
+ "through",
103
+ "during",
104
+ "before",
105
+ "after",
106
+ "above",
107
+ "below",
108
+ "to",
109
+ "from",
110
+ "up",
111
+ "down",
112
+ "in",
113
+ "out",
114
+ "on",
115
+ "off",
116
+ "over",
117
+ "under",
118
+ "again",
119
+ "further",
120
+ "then",
121
+ "once",
122
+ "here",
123
+ "there",
124
+ "when",
125
+ "where",
126
+ "why",
127
+ "how",
128
+ "all",
129
+ "any",
130
+ "both",
131
+ "each",
132
+ "few",
133
+ "more",
134
+ "most",
135
+ "other",
136
+ "some",
137
+ "such",
138
+ "no",
139
+ "nor",
140
+ "not",
141
+ "only",
142
+ "own",
143
+ "same",
144
+ "so",
145
+ "than",
146
+ "too",
147
+ "very",
148
+ "s",
149
+ "t",
150
+ "can",
151
+ "will",
152
+ "just",
153
+ "don",
154
+ "don't",
155
+ "should",
156
+ "should've",
157
+ "now",
158
+ "d",
159
+ "ll",
160
+ "m",
161
+ "o",
162
+ "re",
163
+ "ve",
164
+ "y",
165
+ "ain",
166
+ "aren",
167
+ "aren't",
168
+ "couldn",
169
+ "couldn't",
170
+ "didn",
171
+ "didn't",
172
+ "doesn",
173
+ "doesn't",
174
+ "hadn",
175
+ "hadn't",
176
+ "hasn",
177
+ "hasn't",
178
+ "haven",
179
+ "haven't",
180
+ "isn",
181
+ "isn't",
182
+ "ma",
183
+ "mightn",
184
+ "mightn't",
185
+ "mustn",
186
+ "mustn't",
187
+ "needn",
188
+ "needn't",
189
+ "shan",
190
+ "shan't",
191
+ "shouldn",
192
+ "shouldn't",
193
+ "wasn",
194
+ "wasn't",
195
+ "weren",
196
+ "weren't",
197
+ "won",
198
+ "won't",
199
+ "wouldn",
200
+ "wouldn't",
201
+ "RadioGenoa"
202
+ ],
203
+ "strip_accents": "unicode",
204
+ "token_pattern": "(?u)\\b\\w\\w+\\b",
205
+ "vocabulary": null
206
+ },
207
+ "vocab": {
208
+ "tourists": 1021,
209
+ "see": 880,
210
+ "eternal": 349,
211
+ "thriving": 1004,
212
+ "2700": 23,
213
+ "years": 1138,
214
+ "within": 1126,
215
+ "decade": 273,
216
+ "become": 123,
217
+ "dumping": 319,
218
+ "ground": 437,
219
+ "uncontrolled": 1055,
220
+ "immigration": 498,
221
+ "want": 1098,
222
+ "julius": 553,
223
+ "caesar": 171,
224
+ "back": 109,
225
+ "thousands": 1001,
226
+ "middle": 644,
227
+ "class": 216,
228
+ "soldiers": 920,
229
+ "die": 303,
230
+ "front": 407,
231
+ "offspring": 718,
232
+ "ukrainian": 1049,
233
+ "oligarchs": 721,
234
+ "celebrate": 191,
235
+ "odessa": 715,
236
+ "arcadia": 82,
237
+ "beach": 118,
238
+ "amid": 70,
239
+ "rivers": 847,
240
+ "beer": 125,
241
+ "vodka": 1093,
242
+ "champagne": 197,
243
+ "cocaine": 223,
244
+ "ukraine": 1048,
245
+ "corrupt": 236,
246
+ "countries": 241,
247
+ "world": 1132,
248
+ "afghan": 51,
249
+ "harasses": 451,
250
+ "passengers": 744,
251
+ "train": 1028,
252
+ "uk": 1047,
253
+ "police": 763,
254
+ "officer": 716,
255
+ "knocks": 562,
256
+ "headbutt": 457,
257
+ "cyprus": 258,
258
+ "residents": 833,
259
+ "hunt": 491,
260
+ "syrian": 976,
261
+ "invaders": 527,
262
+ "responsible": 836,
263
+ "murder": 679,
264
+ "rape": 804,
265
+ "harassment": 452,
266
+ "robbery": 851,
267
+ "countless": 240,
268
+ "crimes": 248,
269
+ "fake": 372,
270
+ "refugees": 823,
271
+ "say": 869,
272
+ "enough": 340,
273
+ "african": 54,
274
+ "asian": 95,
275
+ "media": 635,
276
+ "show": 910,
277
+ "old": 720,
278
+ "rummages": 858,
279
+ "trash": 1031,
280
+ "looking": 600,
281
+ "food": 395,
282
+ "live": 591,
283
+ "525": 31,
284
+ "month": 664,
285
+ "young": 1141,
286
+ "hotel": 479,
287
+ "1050": 5,
288
+ "included": 502,
289
+ "paid": 734,
290
+ "us": 1075,
291
+ "giorgia": 426,
292
+ "meloni": 638,
293
+ "intolerable": 523,
294
+ "expense": 361,
295
+ "pensioners": 753,
296
+ "national": 685,
297
+ "geographic": 419,
298
+ "drunk": 316,
299
+ "wants": 1101,
300
+ "take": 978,
301
+ "bus": 169,
302
+ "without": 1127,
303
+ "ticket": 1010,
304
+ "beats": 121,
305
+ "inspectors": 512,
306
+ "stay": 941,
307
+ "service": 889,
308
+ "get": 423,
309
+ "kicked": 556,
310
+ "punched": 794,
311
+ "driver": 314,
312
+ "historic": 467,
313
+ "center": 194,
314
+ "roman": 854,
315
+ "empire": 332,
316
+ "barbarian": 113,
317
+ "hordes": 474,
318
+ "infinite": 508,
319
+ "decline": 277,
320
+ "switzerland": 973,
321
+ "zurich": 1144,
322
+ "raise": 803,
323
+ "muslims": 681,
324
+ "happens": 448,
325
+ "woman": 1128,
326
+ "cheats": 203,
327
+ "must": 682,
328
+ "put": 797,
329
+ "halfway": 441,
330
+ "underground": 1056,
331
+ "hit": 468,
332
+ "face": 367,
333
+ "head": 456,
334
+ "dies": 304,
335
+ "written": 1136,
336
+ "koran": 565,
337
+ "also": 67,
338
+ "whipped": 1119,
339
+ "two": 1045,
340
+ "primitive": 777,
341
+ "barbarians": 114,
342
+ "expelled": 360,
343
+ "spain": 927,
344
+ "cries": 246,
345
+ "racism": 800,
346
+ "shopkeepers": 905,
347
+ "tell": 987,
348
+ "defecate": 278,
349
+ "supermarket": 963,
350
+ "much": 674,
351
+ "enrichment": 343,
352
+ "defecates": 279,
353
+ "public": 792,
354
+ "square": 936,
355
+ "works": 1131,
356
+ "jungle": 555,
357
+ "washes": 1109,
358
+ "genitals": 415,
359
+ "fountain": 400,
360
+ "usually": 1078,
361
+ "mouths": 670,
362
+ "drink": 313,
363
+ "tweets": 1044,
364
+ "censored": 192,
365
+ "germany": 422,
366
+ "german": 420,
367
+ "friends": 406,
368
+ "politicians": 765,
369
+ "hiding": 465,
370
+ "truth": 1038,
371
+ "landed": 569,
372
+ "lampedusa": 567,
373
+ "40": 26,
374
+ "sexual": 891,
375
+ "violence": 1090,
376
+ "work": 1130,
377
+ "make": 614,
378
+ "population": 768,
379
+ "christian": 205,
380
+ "values": 1079,
381
+ "respect": 834,
382
+ "traditions": 1025,
383
+ "family": 375,
384
+ "defense": 283,
385
+ "borders": 149,
386
+ "love": 603,
387
+ "homeland": 471,
388
+ "poland": 762,
389
+ "spread": 935,
390
+ "throughout": 1006,
391
+ "hell": 463,
392
+ "currently": 255,
393
+ "000": 0,
394
+ "hotspot": 481,
395
+ "maximum": 632,
396
+ "capacity": 179,
397
+ "400": 27,
398
+ "places": 755,
399
+ "another": 75,
400
+ "10": 2,
401
+ "left": 579,
402
+ "tunisia": 1040,
403
+ "arriving": 93,
404
+ "real": 814,
405
+ "unprecedented": 1068,
406
+ "apocalypse": 78,
407
+ "climbs": 219,
408
+ "onto": 723,
409
+ "hood": 472,
410
+ "car": 183,
411
+ "wanting": 1100,
412
+ "exasperated": 358,
413
+ "leaves": 577,
414
+ "carrying": 185,
415
+ "top": 1018,
416
+ "incredible": 505,
417
+ "french": 405,
418
+ "welcome": 1114,
419
+ "people": 754,
420
+ "part": 741,
421
+ "problem": 780,
422
+ "yet": 1139,
423
+ "video": 1086,
424
+ "shitting": 899,
425
+ "street": 950,
426
+ "call": 173,
427
+ "cultural": 253,
428
+ "nuclear": 707,
429
+ "scientists": 876,
430
+ "telling": 988,
431
+ "europeans": 353,
432
+ "fuck": 408,
433
+ "armed": 83,
434
+ "stones": 948,
435
+ "iron": 533,
436
+ "clubs": 221,
437
+ "destroy": 298,
438
+ "stuttgart": 953,
439
+ "numerous": 709,
440
+ "officers": 717,
441
+ "injured": 509,
442
+ "chase": 200,
443
+ "block": 140,
444
+ "boat": 142,
445
+ "headed": 458,
446
+ "sicily": 913,
447
+ "send": 885,
448
+ "africa": 53,
449
+ "well": 1115,
450
+ "done": 309,
451
+ "launch": 574,
452
+ "nautical": 687,
453
+ "rockets": 852,
454
+ "flee": 390,
455
+ "chased": 201,
456
+ "captured": 182,
457
+ "normal": 703,
458
+ "country": 242,
459
+ "would": 1134,
460
+ "sent": 887,
461
+ "instead": 513,
462
+ "arrested": 88,
463
+ "free": 403,
464
+ "commit": 230,
465
+ "journalist": 548,
466
+ "admits": 47,
467
+ "eu": 351,
468
+ "told": 1015,
469
+ "film": 384,
470
+ "interview": 521,
471
+ "admit": 46,
472
+ "camera": 176,
473
+ "economic": 324,
474
+ "reasons": 817,
475
+ "fleeing": 391,
476
+ "war": 1102,
477
+ "censorship": 193,
478
+ "misinformation": 656,
479
+ "transferred": 1030,
480
+ "bologna": 146,
481
+ "tunisian": 1041,
482
+ "nigerian": 700,
483
+ "clash": 214,
484
+ "harshly": 454,
485
+ "ethnic": 350,
486
+ "soon": 923,
487
+ "happen": 445,
488
+ "neighborhood": 694,
489
+ "images": 496,
490
+ "believe": 129,
491
+ "fairy": 371,
492
+ "tale": 981,
493
+ "poor": 766,
494
+ "refugee": 822,
495
+ "tales": 982,
496
+ "days": 269,
497
+ "15": 9,
498
+ "550": 32,
499
+ "night": 701,
500
+ "30": 24,
501
+ "minutes": 655,
502
+ "20": 18,
503
+ "boats": 143,
504
+ "arrived": 92,
505
+ "1200": 7,
506
+ "500": 29,
507
+ "crotone": 251,
508
+ "ngos": 699,
509
+ "unloaded": 1065,
510
+ "800": 34,
511
+ "total": 1019,
512
+ "18": 15,
513
+ "050": 1,
514
+ "landings": 570,
515
+ "underway": 1057,
516
+ "clashes": 215,
517
+ "unemployed": 1059,
518
+ "removed": 830,
519
+ "poverty": 770,
520
+ "allowance": 63,
521
+ "time": 1011,
522
+ "allowed": 64,
523
+ "190": 16,
524
+ "cost": 237,
525
+ "moved": 671,
526
+ "subsidies": 954,
527
+ "italians": 542,
528
+ "africans": 55,
529
+ "shows": 911,
530
+ "defend": 281,
531
+ "warm": 1104,
532
+ "hearts": 461,
533
+ "still": 944,
534
+ "hope": 473,
535
+ "terrible": 991,
536
+ "brakel": 154,
537
+ "belgium": 127,
538
+ "elderly": 328,
539
+ "man": 618,
540
+ "bench": 130,
541
+ "faces": 368,
542
+ "punches": 795,
543
+ "kicks": 557,
544
+ "comes": 228,
545
+ "aid": 56,
546
+ "scum": 878,
547
+ "tracked": 1023,
548
+ "prosecuted": 785,
549
+ "locked": 594,
550
+ "dozens": 312,
551
+ "towards": 1022,
552
+ "always": 68,
553
+ "endless": 335,
554
+ "new": 696,
555
+ "arrivals": 90,
556
+ "950": 37,
557
+ "week": 1113,
558
+ "enriched": 341,
559
+ "pope": 767,
560
+ "francis": 402,
561
+ "visions": 1092,
562
+ "immigrant": 497,
563
+ "alarmist": 59,
564
+ "propaganda": 783,
565
+ "reality": 815,
566
+ "remind": 828,
567
+ "vatican": 1082,
568
+ "protected": 787,
569
+ "17": 12,
570
+ "meter": 642,
571
+ "walls": 1096,
572
+ "host": 476,
573
+ "home": 470,
574
+ "polish": 764,
575
+ "mep": 640,
576
+ "dominik": 308,
577
+ "tarczynski": 985,
578
+ "silences": 915,
579
+ "wanted": 1099,
580
+ "dump": 317,
581
+ "illegal": 494,
582
+ "doctors": 307,
583
+ "engineers": 337,
584
+ "pay": 751,
585
+ "save": 865,
586
+ "explains": 363,
587
+ "happening": 447,
588
+ "talks": 983,
589
+ "business": 170,
590
+ "deserves": 296,
591
+ "attention": 102,
592
+ "luxury": 606,
593
+ "hotels": 480,
594
+ "telford": 986,
595
+ "many": 620,
596
+ "brits": 163,
597
+ "unable": 1050,
598
+ "ends": 336,
599
+ "meet": 637,
600
+ "scandalous": 872,
601
+ "thing": 997,
602
+ "beyond": 136,
603
+ "la": 566,
604
+ "spezia": 930,
605
+ "threatens": 1002,
606
+ "increasingly": 504,
607
+ "john": 545,
608
+ "paul": 750,
609
+ "ii": 493,
610
+ "prophecy": 784,
611
+ "march": 621,
612
+ "1993": 17,
613
+ "monsignor": 663,
614
+ "longhi": 598,
615
+ "church": 207,
616
+ "third": 1000,
617
+ "millennium": 651,
618
+ "afflicted": 50,
619
+ "deadly": 271,
620
+ "plague": 756,
621
+ "called": 174,
622
+ "islamism": 535,
623
+ "invade": 524,
624
+ "saw": 868,
625
+ "coming": 229,
626
+ "west": 1117,
627
+ "east": 322,
628
+ "morocco": 667,
629
+ "libya": 585,
630
+ "egypt": 326,
631
+ "eastern": 323,
632
+ "shadow": 892,
633
+ "reign": 825,
634
+ "true": 1037,
635
+ "warned": 1105,
636
+ "says": 870,
637
+ "lies": 587,
638
+ "shamelessly": 894,
639
+ "army": 85,
640
+ "men": 639,
641
+ "ready": 813,
642
+ "european": 352,
643
+ "suicide": 962,
644
+ "imposed": 501,
645
+ "needs": 693,
646
+ "good": 434,
647
+ "psychiatrist": 791,
648
+ "tries": 1034,
649
+ "rob": 848,
650
+ "bar": 112,
651
+ "takes": 980,
652
+ "hostage": 477,
653
+ "customers": 256,
654
+ "beat": 119,
655
+ "runs": 859,
656
+ "away": 108,
657
+ "rat": 808,
658
+ "nationality": 686,
659
+ "unknown": 1063,
660
+ "joke": 546,
661
+ "france": 401,
662
+ "masturbates": 631,
663
+ "park": 740,
664
+ "reaction": 811,
665
+ "present": 775,
666
+ "rightly": 845,
667
+ "furious": 412,
668
+ "progress": 782,
669
+ "calm": 175,
670
+ "sea": 879,
671
+ "around": 86,
672
+ "100": 3,
673
+ "additional": 45,
674
+ "5000": 30,
675
+ "male": 615,
676
+ "expected": 359,
677
+ "next": 697,
678
+ "asylum": 97,
679
+ "seekers": 882,
680
+ "defecating": 280,
681
+ "milan": 648,
682
+ "proud": 790,
683
+ "action": 42,
684
+ "souvenir": 926,
685
+ "selfie": 884,
686
+ "ass": 96,
687
+ "could": 238,
688
+ "child": 204,
689
+ "school": 875,
690
+ "ngo": 698,
691
+ "ships": 898,
692
+ "mediterranean": 636,
693
+ "collecting": 225,
694
+ "subsidized": 955,
695
+ "government": 435,
696
+ "let": 583,
697
+ "afd": 48,
698
+ "wins": 1124,
699
+ "elections": 329,
700
+ "destroys": 299,
701
+ "cars": 186,
702
+ "hammer": 443,
703
+ "boredom": 150,
704
+ "humanity": 489,
705
+ "dumps": 320,
706
+ "ancona": 72,
707
+ "vast": 1081,
708
+ "majority": 613,
709
+ "germans": 421,
710
+ "support": 964,
711
+ "declare": 276,
712
+ "norwegian": 705,
713
+ "geo": 418,
714
+ "barents": 115,
715
+ "collects": 226,
716
+ "libyan": 586,
717
+ "territorial": 992,
718
+ "waters": 1112,
719
+ "funds": 411,
720
+ "following": 394,
721
+ "operate": 725,
722
+ "sos": 924,
723
+ "rise": 846,
724
+ "mission": 658,
725
+ "lifeline": 588,
726
+ "watch": 1111,
727
+ "unitedrescue": 1061,
728
+ "eye": 366,
729
+ "resq": 837,
730
+ "louise": 602,
731
+ "michel": 643,
732
+ "resqship": 838,
733
+ "spanish": 928,
734
+ "open": 724,
735
+ "arms": 84,
736
+ "uno": 1067,
737
+ "proactiva": 779,
738
+ "aita": 57,
739
+ "mari": 624,
740
+ "salvamento": 862,
741
+ "maritimo": 625,
742
+ "humanitario": 488,
743
+ "ocean": 713,
744
+ "viking": 1088,
745
+ "english": 338,
746
+ "aurora": 104,
747
+ "relentlessly": 827,
748
+ "besides": 134,
749
+ "finances": 386,
750
+ "fleet": 392,
751
+ "usual": 1077,
752
+ "suspect": 969,
753
+ "knife": 560,
754
+ "receives": 819,
755
+ "double": 311,
756
+ "electric": 330,
757
+ "shock": 900,
758
+ "reward": 843,
759
+ "mare": 623,
760
+ "jonio": 547,
761
+ "bribe": 160,
762
+ "125": 8,
763
+ "interceptions": 517,
764
+ "judiciary": 552,
765
+ "captain": 180,
766
+ "luca": 605,
767
+ "casarini": 187,
768
+ "earned": 321,
769
+ "27": 22,
770
+ "made": 610,
771
+ "splash": 933,
772
+ "practice": 772,
773
+ "received": 818,
774
+ "transfer": 1029,
775
+ "danish": 262,
776
+ "oil": 719,
777
+ "tanker": 984,
778
+ "unload": 1064,
779
+ "multiple": 678,
780
+ "criminal": 249,
781
+ "awarded": 106,
782
+ "saving": 867,
783
+ "machetes": 609,
784
+ "knives": 561,
785
+ "brussels": 166,
786
+ "loads": 593,
787
+ "200": 19,
788
+ "heads": 459,
789
+ "genoa": 416,
790
+ "go": 432,
791
+ "subsidizes": 956,
792
+ "waiting": 1095,
793
+ "activists": 43,
794
+ "entertain": 344,
795
+ "sensual": 886,
796
+ "dances": 259,
797
+ "unauthorized": 1054,
798
+ "demonstration": 288,
799
+ "turin": 1042,
800
+ "wing": 1123,
801
+ "extremists": 365,
802
+ "insult": 514,
803
+ "spit": 931,
804
+ "force": 396,
805
+ "blockade": 141,
806
+ "throw": 1007,
807
+ "objects": 711,
808
+ "restore": 840,
809
+ "order": 727,
810
+ "sailing": 861,
811
+ "ship": 897,
812
+ "nadir": 683,
813
+ "owned": 731,
814
+ "unloads": 1066,
815
+ "shame": 893,
816
+ "outrage": 729,
817
+ "hostile": 478,
818
+ "act": 41,
819
+ "livorno": 592,
820
+ "scabies": 871,
821
+ "2023": 20,
822
+ "human": 487,
823
+ "traffickers": 1027,
824
+ "ports": 769,
825
+ "civitavecchia": 213,
826
+ "brindisi": 161,
827
+ "bari": 116,
828
+ "ortona": 728,
829
+ "ravenna": 809,
830
+ "catania": 189,
831
+ "clear": 217,
832
+ "intent": 516,
833
+ "destabilize": 297,
834
+ "1000": 4,
835
+ "el": 327,
836
+ "hierro": 466,
837
+ "island": 537,
838
+ "planned": 758,
839
+ "female": 383,
840
+ "judge": 551,
841
+ "ms": 673,
842
+ "apostolico": 79,
843
+ "freed": 404,
844
+ "three": 1003,
845
+ "criminals": 250,
846
+ "facing": 369,
847
+ "deportation": 291,
848
+ "past": 745,
849
+ "participated": 742,
850
+ "violent": 1091,
851
+ "far": 378,
852
+ "demonstrations": 289,
853
+ "favor": 380,
854
+ "missing": 657,
855
+ "san": 863,
856
+ "bonifacio": 147,
857
+ "verona": 1084,
858
+ "families": 374,
859
+ "streets": 951,
860
+ "bring": 162,
861
+ "crime": 247,
862
+ "degradation": 285,
863
+ "occupation": 712,
864
+ "houses": 484,
865
+ "drug": 315,
866
+ "dealing": 272,
867
+ "muggings": 675,
868
+ "robberies": 850,
869
+ "thefts": 995,
870
+ "attacks": 100,
871
+ "citizens": 209,
872
+ "rapes": 806,
873
+ "kinds": 559,
874
+ "cities": 208,
875
+ "especially": 347,
876
+ "completely": 232,
877
+ "deportations": 292,
878
+ "needed": 692,
879
+ "viktor": 1089,
880
+ "orban": 726,
881
+ "ursula": 1074,
882
+ "von": 1094,
883
+ "der": 295,
884
+ "leyen": 584,
885
+ "legally": 580,
886
+ "raped": 805,
887
+ "hungary": 490,
888
+ "forcing": 398,
889
+ "migration": 647,
890
+ "pact": 733,
891
+ "compromise": 233,
892
+ "today": 1014,
893
+ "upcoming": 1072,
894
+ "migrants": 646,
895
+ "bureaucrats": 167,
896
+ "right": 844,
897
+ "rejected": 826,
898
+ "250": 21,
899
+ "balkan": 111,
900
+ "route": 856,
901
+ "malta": 617,
902
+ "affects": 49,
903
+ "queues": 798,
904
+ "explain": 362,
905
+ "legia": 581,
906
+ "warsaw": 1106,
907
+ "fans": 377,
908
+ "berlin": 132,
909
+ "zero": 1143,
910
+ "tolerance": 1016,
911
+ "coast": 222,
912
+ "guard": 439,
913
+ "chases": 202,
914
+ "fails": 370,
915
+ "capture": 181,
916
+ "hours": 482,
917
+ "unacceptable": 1051,
918
+ "doors": 310,
919
+ "closed": 220,
920
+ "house": 483,
921
+ "50": 28,
922
+ "invades": 528,
923
+ "pozzallo": 771,
924
+ "terrorists": 994,
925
+ "dangers": 261,
926
+ "becoming": 124,
927
+ "evident": 357,
928
+ "cannot": 178,
929
+ "accept": 39,
930
+ "migrant": 645,
931
+ "quota": 799,
932
+ "system": 977,
933
+ "ghettos": 424,
934
+ "afghans": 52,
935
+ "pakistanis": 735,
936
+ "udine": 1046,
937
+ "chairs": 196,
938
+ "dumped": 318,
939
+ "brazil": 157,
940
+ "attacked": 98,
941
+ "pram": 773,
942
+ "pointed": 761,
943
+ "father": 379,
944
+ "wounding": 1135,
945
+ "hand": 444,
946
+ "managed": 619,
947
+ "disarm": 305,
948
+ "kill": 558,
949
+ "attacker": 99,
950
+ "defending": 282,
951
+ "daughter": 265,
952
+ "every": 355,
953
+ "white": 1120,
954
+ "alive": 61,
955
+ "planet": 757,
956
+ "motherfuckers": 668,
957
+ "iq": 531,
958
+ "islamic": 534,
959
+ "invader": 526,
960
+ "heart": 460,
961
+ "patriots": 749,
962
+ "angry": 73,
963
+ "london": 595,
964
+ "scenes": 874,
965
+ "worthy": 1133,
966
+ "civilized": 212,
967
+ "day": 267,
968
+ "belgrade": 128,
969
+ "traditional": 1024,
970
+ "algerian": 60,
971
+ "mohammed": 660,
972
+ "breaks": 158,
973
+ "swedish": 972,
974
+ "leaving": 578,
975
+ "hate": 455,
976
+ "traffic": 1026,
977
+ "wardens": 1103,
978
+ "birmingham": 137,
979
+ "caliphate": 172,
980
+ "arabs": 81,
981
+ "lubeck": 604,
982
+ "hide": 464,
983
+ "reason": 816,
984
+ "publish": 793,
985
+ "sweden": 971,
986
+ "malmo": 616,
987
+ "shouting": 908,
988
+ "allah": 62,
989
+ "akbar": 58,
990
+ "en": 334,
991
+ "masse": 630,
992
+ "bradford": 153,
993
+ "forced": 397,
994
+ "multicultural": 677,
995
+ "society": 919,
996
+ "mess": 641,
997
+ "oceanic": 714,
998
+ "crowd": 252,
999
+ "decided": 274,
1000
+ "change": 198,
1001
+ "better": 135,
1002
+ "palestinians": 738,
1003
+ "marching": 622,
1004
+ "body": 145,
1005
+ "israeli": 541,
1006
+ "leaders": 576,
1007
+ "israel": 540,
1008
+ "peace": 752,
1009
+ "minister": 652,
1010
+ "announced": 74,
1011
+ "hamas": 442,
1012
+ "militant": 649,
1013
+ "group": 438,
1014
+ "started": 938,
1015
+ "militants": 650,
1016
+ "invaded": 525,
1017
+ "southern": 925,
1018
+ "shooting": 903,
1019
+ "everyone": 356,
1020
+ "terrorist": 993,
1021
+ "happened": 446,
1022
+ "aware": 107,
1023
+ "july": 554,
1024
+ "jihad": 544,
1025
+ "massacre": 628,
1026
+ "civilians": 211,
1027
+ "carried": 184,
1028
+ "rotterdam": 855,
1029
+ "paris": 739,
1030
+ "replace": 832,
1031
+ "rag": 802,
1032
+ "flag": 389,
1033
+ "nation": 684,
1034
+ "gentlemen": 417,
1035
+ "ones": 722,
1036
+ "land": 568,
1037
+ "impose": 500,
1038
+ "culture": 254,
1039
+ "know": 563,
1040
+ "supporters": 965,
1041
+ "huge": 486,
1042
+ "madrid": 612,
1043
+ "bodies": 144,
1044
+ "massacred": 629,
1045
+ "laugh": 573,
1046
+ "pride": 776,
1047
+ "joy": 550,
1048
+ "intifada": 522,
1049
+ "victory": 1085,
1050
+ "revolt": 842,
1051
+ "pro": 778,
1052
+ "extremist": 364,
1053
+ "students": 952,
1054
+ "sapienza": 864,
1055
+ "university": 1062,
1056
+ "jhiad": 543,
1057
+ "gaza": 414,
1058
+ "blm": 139,
1059
+ "canada": 177,
1060
+ "troublemakers": 1036,
1061
+ "surrounds": 968,
1062
+ "pushes": 796,
1063
+ "insults": 515,
1064
+ "vienna": 1087,
1065
+ "marseille": 627,
1066
+ "amsterdam": 71,
1067
+ "arrests": 89,
1068
+ "austria": 105,
1069
+ "indiscriminate": 506,
1070
+ "brought": 165,
1071
+ "dark": 263,
1072
+ "times": 1012,
1073
+ "arrive": 91,
1074
+ "surrounded": 967,
1075
+ "fanatics": 376,
1076
+ "use": 1076,
1077
+ "mothers": 669,
1078
+ "daughters": 266,
1079
+ "waste": 1110,
1080
+ "crack": 243,
1081
+ "burn": 168,
1082
+ "symbol": 974,
1083
+ "full": 410,
1084
+ "arras": 87,
1085
+ "dead": 270,
1086
+ "several": 890,
1087
+ "shouted": 907,
1088
+ "stabbed": 937,
1089
+ "unarmed": 1053,
1090
+ "responded": 835,
1091
+ "invoked": 530,
1092
+ "chaos": 199,
1093
+ "madness": 611,
1094
+ "looks": 601,
1095
+ "arab": 80,
1096
+ "unrecognizable": 1069,
1097
+ "muslim": 680,
1098
+ "refuses": 824,
1099
+ "remove": 829,
1100
+ "palestinian": 737,
1101
+ "scarf": 873,
1102
+ "seized": 883,
1103
+ "mob": 659,
1104
+ "attempts": 101,
1105
+ "lynch": 607,
1106
+ "tomorrow": 1017,
1107
+ "etc": 348,
1108
+ "look": 599,
1109
+ "protesters": 788,
1110
+ "react": 810,
1111
+ "decisively": 275,
1112
+ "islamist": 536,
1113
+ "shouts": 909,
1114
+ "come": 227,
1115
+ "sharia": 896,
1116
+ "overnight": 730,
1117
+ "solved": 922,
1118
+ "shout": 906,
1119
+ "throwing": 1008,
1120
+ "molotov": 661,
1121
+ "cocktails": 224,
1122
+ "various": 1080,
1123
+ "destructions": 300,
1124
+ "palestine": 736,
1125
+ "minority": 653,
1126
+ "western": 1118,
1127
+ "necessary": 690,
1128
+ "defenseless": 284,
1129
+ "enjoys": 339,
1130
+ "benefits": 131,
1131
+ "law": 575,
1132
+ "infernal": 507,
1133
+ "heat": 462,
1134
+ "record": 821,
1135
+ "temperature": 989,
1136
+ "climate": 218,
1137
+ "marmolada": 626,
1138
+ "august": 103,
1139
+ "degrees": 286,
1140
+ "feels": 382,
1141
+ "christmas": 206,
1142
+ "continue": 235,
1143
+ "shocked": 901,
1144
+ "165": 11,
1145
+ "11": 6,
1146
+ "months": 665,
1147
+ "please": 759,
1148
+ "patriot": 748,
1149
+ "recent": 820,
1150
+ "170": 13,
1151
+ "last": 572,
1152
+ "80": 33,
1153
+ "175": 14,
1154
+ "substitution": 958,
1155
+ "beautiful": 122,
1156
+ "islands": 538,
1157
+ "turned": 1043,
1158
+ "trojan": 1035,
1159
+ "horse": 475,
1160
+ "brawl": 156,
1161
+ "guns": 440,
1162
+ "invading": 529,
1163
+ "subsidy": 957,
1164
+ "give": 429,
1165
+ "money": 662,
1166
+ "zelensky": 1142,
1167
+ "first": 387,
1168
+ "devastate": 301,
1169
+ "nyc": 710,
1170
+ "mayor": 634,
1171
+ "american": 69,
1172
+ "eric": 346,
1173
+ "adams": 44,
1174
+ "democratic": 287,
1175
+ "party": 743,
1176
+ "york": 1140,
1177
+ "impacted": 499,
1178
+ "supremacist": 966,
1179
+ "racist": 801,
1180
+ "scourge": 877,
1181
+ "said": 860,
1182
+ "35": 25,
1183
+ "deported": 293,
1184
+ "date": 264,
1185
+ "border": 148,
1186
+ "ventimiglia": 1083,
1187
+ "alone": 66,
1188
+ "state": 939,
1189
+ "emergency": 331,
1190
+ "deploy": 290,
1191
+ "warships": 1107,
1192
+ "8000": 35,
1193
+ "160": 10,
1194
+ "almost": 65,
1195
+ "number": 708,
1196
+ "words": 1129,
1197
+ "longer": 597,
1198
+ "taken": 979,
1199
+ "journalists": 549,
1200
+ "false": 373,
1201
+ "protests": 789,
1202
+ "across": 40,
1203
+ "deputy": 294,
1204
+ "tourism": 1020,
1205
+ "fishing": 388,
1206
+ "nothing": 706,
1207
+ "nobody": 702,
1208
+ "patience": 747,
1209
+ "unworthy": 1071,
1210
+ "profit": 781,
1211
+ "anyone": 76,
1212
+ "thinks": 999,
1213
+ "witch": 1125,
1214
+ "solution": 921,
1215
+ "suffers": 961,
1216
+ "stockholm": 945,
1217
+ "syndrome": 975,
1218
+ "create": 245,
1219
+ "termini": 990,
1220
+ "station": 940,
1221
+ "harass": 449,
1222
+ "steal": 942,
1223
+ "necklaces": 691,
1224
+ "girls": 428,
1225
+ "serious": 888,
1226
+ "episode": 345,
1227
+ "dictatorships": 302,
1228
+ "nazi": 688,
1229
+ "silence": 914,
1230
+ "succeed": 960,
1231
+ "travel": 1032,
1232
+ "illegally": 495,
1233
+ "ireland": 532,
1234
+ "netherlands": 695,
1235
+ "bernd": 133,
1236
+ "baumann": 117,
1237
+ "think": 998,
1238
+ "protect": 786,
1239
+ "artificially": 94,
1240
+ "unaccompanied": 1052,
1241
+ "minors": 654,
1242
+ "garrison": 413,
1243
+ "brescia": 159,
1244
+ "social": 918,
1245
+ "multi": 676,
1246
+ "wan": 1097,
1247
+ "globalist": 431,
1248
+ "maybe": 633,
1249
+ "north": 704,
1250
+ "try": 1039,
1251
+ "tobacconist": 1013,
1252
+ "beaten": 120,
1253
+ "sicilians": 912,
1254
+ "rules": 857,
1255
+ "story": 949,
1256
+ "harassed": 450,
1257
+ "committed": 231,
1258
+ "rapists": 807,
1259
+ "subway": 959,
1260
+ "fed": 381,
1261
+ "innumerable": 511,
1262
+ "harassments": 453,
1263
+ "roma": 853,
1264
+ "shard": 895,
1265
+ "bottle": 151,
1266
+ "shoot": 902,
1267
+ "injures": 510,
1268
+ "glass": 430,
1269
+ "urinates": 1073,
1270
+ "near": 689,
1271
+ "long": 596,
1272
+ "crap": 244,
1273
+ "isolated": 539,
1274
+ "case": 188,
1275
+ "discovered": 306,
1276
+ "stealing": 943,
1277
+ "apartment": 77,
1278
+ "lynched": 608,
1279
+ "moroccan": 666,
1280
+ "underwear": 1058,
1281
+ "throws": 1009,
1282
+ "restaurant": 839,
1283
+ "stole": 946,
1284
+ "bag": 110,
1285
+ "hits": 469,
1286
+ "presence": 774,
1287
+ "lights": 589,
1288
+ "wash": 1108,
1289
+ "windows": 1122,
1290
+ "reacts": 812,
1291
+ "spitting": 932,
1292
+ "fucking": 409,
1293
+ "bitch": 138,
1294
+ "cut": 257,
1295
+ "throat": 1005,
1296
+ "finally": 385,
1297
+ "large": 571,
1298
+ "stone": 947,
1299
+ "grandmother": 436,
1300
+ "catches": 190,
1301
+ "slaps": 917,
1302
+ "repeatedly": 831,
1303
+ "thieves": 996,
1304
+ "saved": 866,
1305
+ "unfortunately": 1060,
1306
+ "intervenes": 520,
1307
+ "civic": 210,
1308
+ "education": 325,
1309
+ "lesson": 582,
1310
+ "suspects": 970,
1311
+ "unsafe": 1070,
1312
+ "dangerous": 260,
1313
+ "seeker": 881,
1314
+ "intervene": 518,
1315
+ "trento": 1033,
1316
+ "enricher": 342,
1317
+ "shop": 904,
1318
+ "window": 1121,
1319
+ "employees": 333,
1320
+ "owner": 732,
1321
+ "known": 564,
1322
+ "pastry": 746,
1323
+ "certain": 195,
1324
+ "point": 760,
1325
+ "went": 1116,
1326
+ "behind": 126,
1327
+ "counter": 239,
1328
+ "brandished": 155,
1329
+ "spatula": 929,
1330
+ "intervened": 519,
1331
+ "spot": 934,
1332
+ "identified": 492,
1333
+ "however": 485,
1334
+ "even": 354,
1335
+ "inconceivable": 503,
1336
+ "absurd": 38,
1337
+ "boy": 152,
1338
+ "slap": 916,
1339
+ "girlfriend": 427,
1340
+ "florence": 393,
1341
+ "91": 36,
1342
+ "year": 1137,
1343
+ "robbed": 849,
1344
+ "broad": 164,
1345
+ "daylight": 268,
1346
+ "congratulations": 234,
1347
+ "mr": 672,
1348
+ "giampaolo": 425,
1349
+ "fought": 399,
1350
+ "lion": 590,
1351
+ "gold": 433,
1352
+ "returned": 841
1353
+ }
1354
+ }
1355
+ }
topic_embeddings.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f43053e625c115cbaef03754afa2c60e160c07369637ccf989278d7c41c27f41
3
+ size 16472
topics.json ADDED
@@ -0,0 +1,301 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "topic_representations": {
3
+ "-1": [
4
+ [
5
+ "lampedusa",
6
+ 0.5905419588088989
7
+ ],
8
+ [
9
+ "traffickers",
10
+ 0.5594484806060791
11
+ ],
12
+ [
13
+ "refugees",
14
+ 0.5346866846084595
15
+ ],
16
+ [
17
+ "pope",
18
+ 0.5260183811187744
19
+ ],
20
+ [
21
+ "hungary",
22
+ 0.4914746582508087
23
+ ]
24
+ ],
25
+ "0": [
26
+ [
27
+ "jihad",
28
+ 0.6562311053276062
29
+ ],
30
+ [
31
+ "hamas",
32
+ 0.6371703743934631
33
+ ],
34
+ [
35
+ "terrorists",
36
+ 0.5941577553749084
37
+ ],
38
+ [
39
+ "mohammed",
40
+ 0.5294718742370605
41
+ ],
42
+ [
43
+ "brussels",
44
+ 0.49078524112701416
45
+ ]
46
+ ],
47
+ "1": [
48
+ [
49
+ "lampedusa",
50
+ 0.6750643253326416
51
+ ],
52
+ [
53
+ "invaders",
54
+ 0.539577841758728
55
+ ],
56
+ [
57
+ "refugees",
58
+ 0.5278039574623108
59
+ ],
60
+ [
61
+ "african",
62
+ 0.4679066240787506
63
+ ],
64
+ [
65
+ "unprecedented",
66
+ 0.443244606256485
67
+ ]
68
+ ],
69
+ "2": [
70
+ [
71
+ "sicilians",
72
+ 0.6024553775787354
73
+ ],
74
+ [
75
+ "african",
76
+ 0.5419142842292786
77
+ ],
78
+ [
79
+ "robbed",
80
+ 0.5358157753944397
81
+ ],
82
+ [
83
+ "rapists",
84
+ 0.5298659801483154
85
+ ],
86
+ [
87
+ "slaps",
88
+ 0.49932172894477844
89
+ ]
90
+ ]
91
+ },
92
+ "topics": [
93
+ 0,
94
+ 2,
95
+ 1,
96
+ 0,
97
+ 2,
98
+ 2,
99
+ -1,
100
+ 1,
101
+ 2,
102
+ -1,
103
+ 2,
104
+ 2,
105
+ 1,
106
+ 1,
107
+ 1,
108
+ 1,
109
+ 2,
110
+ 1,
111
+ 1,
112
+ -1,
113
+ 1,
114
+ -1,
115
+ 0,
116
+ 1,
117
+ 2,
118
+ 2,
119
+ -1,
120
+ -1,
121
+ 2,
122
+ 0,
123
+ 0,
124
+ 0,
125
+ -1,
126
+ -1,
127
+ 0,
128
+ -1,
129
+ 1,
130
+ 2,
131
+ 2,
132
+ -1,
133
+ -1,
134
+ 2,
135
+ -1,
136
+ -1,
137
+ 1,
138
+ 1,
139
+ -1,
140
+ 1,
141
+ -1,
142
+ -1,
143
+ -1,
144
+ -1,
145
+ 2,
146
+ -1,
147
+ -1,
148
+ 1,
149
+ -1,
150
+ -1,
151
+ -1,
152
+ 1,
153
+ 2,
154
+ 1,
155
+ -1,
156
+ 0,
157
+ 1,
158
+ -1,
159
+ 1,
160
+ 1,
161
+ -1,
162
+ 1,
163
+ -1,
164
+ -1,
165
+ -1,
166
+ -1,
167
+ -1,
168
+ 0,
169
+ -1,
170
+ -1,
171
+ -1,
172
+ 1,
173
+ 1,
174
+ -1,
175
+ 1,
176
+ 2,
177
+ -1,
178
+ -1,
179
+ -1,
180
+ -1,
181
+ -1,
182
+ -1,
183
+ 1,
184
+ -1,
185
+ 0,
186
+ -1,
187
+ -1,
188
+ -1,
189
+ -1,
190
+ -1,
191
+ -1,
192
+ -1,
193
+ -1,
194
+ -1,
195
+ -1,
196
+ -1,
197
+ -1,
198
+ -1,
199
+ -1,
200
+ 1,
201
+ -1,
202
+ -1,
203
+ -1,
204
+ 0,
205
+ -1,
206
+ -1,
207
+ -1,
208
+ -1,
209
+ 2,
210
+ -1,
211
+ -1,
212
+ -1,
213
+ 2,
214
+ 0,
215
+ 0,
216
+ 0,
217
+ 0,
218
+ 0,
219
+ 0,
220
+ 0,
221
+ 0,
222
+ 0,
223
+ 0,
224
+ -1,
225
+ -1,
226
+ 0,
227
+ 0,
228
+ 0,
229
+ 0,
230
+ -1,
231
+ -1,
232
+ 0,
233
+ -1,
234
+ 0,
235
+ 0,
236
+ 0,
237
+ -1,
238
+ 2,
239
+ 0,
240
+ 0,
241
+ 0,
242
+ 0,
243
+ 0,
244
+ 0,
245
+ 0,
246
+ 2,
247
+ 0,
248
+ 0,
249
+ 0,
250
+ 0,
251
+ 0,
252
+ 0,
253
+ 0,
254
+ 0,
255
+ 0,
256
+ 0,
257
+ 0,
258
+ -1,
259
+ 0,
260
+ 0,
261
+ 0,
262
+ -1
263
+ ],
264
+ "topic_sizes": {
265
+ "0": 50,
266
+ "2": 20,
267
+ "1": 26,
268
+ "-1": 74
269
+ },
270
+ "topic_mapper": [
271
+ [
272
+ -1,
273
+ -1,
274
+ -1
275
+ ],
276
+ [
277
+ 0,
278
+ 0,
279
+ 0
280
+ ],
281
+ [
282
+ 1,
283
+ 1,
284
+ 1
285
+ ],
286
+ [
287
+ 2,
288
+ 2,
289
+ 2
290
+ ]
291
+ ],
292
+ "topic_labels": {
293
+ "-1": "-1_lampedusa_traffickers_refugees_pope",
294
+ "0": "0_jihad_hamas_terrorists_mohammed",
295
+ "1": "1_lampedusa_invaders_refugees_african",
296
+ "2": "2_sicilians_african_robbed_rapists"
297
+ },
298
+ "custom_labels": null,
299
+ "_outliers": 1,
300
+ "topic_aspects": {}
301
+ }