MorcuendeA commited on
Commit
e891d0c
·
verified ·
1 Parent(s): 0de825d

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +290 -1
README.md CHANGED
@@ -28,5 +28,294 @@ dataset_info:
28
  dataset_size: 1611105.0
29
  ---
30
  # Dataset Card for "ConspiraText-ES"
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
31
 
32
- [More Information needed](https://github.com/huggingface/datasets/blob/main/CONTRIBUTING.md#how-to-contribute-to-the-dataset-cards)
 
28
  dataset_size: 1611105.0
29
  ---
30
  # Dataset Card for "ConspiraText-ES"
31
+ ---
32
+ annotations_creators:
33
+ - machine-generated
34
+ language_creators:
35
+ - machine-generated
36
+ languages:
37
+ - es
38
+ licenses:
39
+ - cc-by-4.0
40
+ multilinguality:
41
+ - monolingual
42
+ pretty_name: ConspiraText-ES
43
+ size_categories:
44
+ - 1K<n<10K
45
+ source_datasets:
46
+ - original
47
+ task_categories:
48
+ - text-classification
49
+ task_ids:
50
+ - binary-classification
51
+ ---
52
+
53
+ # Dataset Card for ConspiraText-ES
54
+
55
+ ## Table of Contents
56
+
57
+ - [Dataset Description](#dataset-description)
58
+ - [Dataset Structure](#dataset-structure)
59
+ - [Dataset Creation](#dataset-creation)
60
+ - [Considerations for Using the Data](#considerations-for-using-the-data)
61
+ - [Additional Information](#additional-information)
62
+
63
+ ## Dataset Description
64
+
65
+ **Homepage:** Not available
66
+ **Repository:** Not available
67
+ **Paper:** Not available
68
+ **Leaderboard:** Not available
69
+ **Point of Contact:** Not available
70
+
71
+ ### Dataset Summary
72
+
73
+ ConspiraText-ES is a synthetic Spanish-language dataset, using DeepSeeker R1 0528, containing short, tweet-style messages related to 15 common conspiracy topics paired with their rational refutations. Each message is labeled as either conspiratorial or rational.
74
+
75
+ The dataset is balanced and designed for binary classification tasks.
76
+
77
+ ### Supported Tasks and Leaderboards
78
+
79
+ - Text classification (binary): Detect conspiratorial vs. rational statements.
80
+
81
+ ### Languages
82
+
83
+ - Spanish (`es`)
84
+
85
+ ## Dataset Structure
86
+
87
+ ### Data Instances
88
+
89
+ Each data instance consists of a short Spanish text message (tweet style) and a binary label indicating whether the message is conspiratorial (1) or rational (0).
90
+
91
+ text (string): A short Spanish text message.
92
+
93
+ label (int): Class label where 0 = rational, 1 = conspiratorial.
94
+
95
+ ### Data Splits
96
+
97
+ | Split | Total Samples | Class 0 | Class 1 |
98
+ |------------|---------------|---------|---------|
99
+ | Train | 4,220 | 2,065 | 2,155 |
100
+ | Validation | 528 | 262 | 266 |
101
+ | Test | 528 | 263 | 265 |
102
+
103
+
104
+ ## Dataset Creation
105
+
106
+ ### Curation Rationale
107
+
108
+ The dataset was created as a personal, experimental synthetic resource to simulate conspiratorial and rational discourse styles on key social topics. It aims to facilitate research in misinformation, discourse classification, and bias detection.
109
+
110
+ Financial Elites
111
+ Conspiracy: They control governments through debt.
112
+ Refutation: Complex and transparent economic processes.
113
+
114
+ Climate Change
115
+ Conspiracy: An excuse for a global government.
116
+ Refutation: A real and urgent scientific phenomenon.
117
+
118
+ Processed Foods
119
+ Conspiracy: Designed to reduce fertility.
120
+ Refutation: Regulated food safety.
121
+
122
+ Education System
123
+ Conspiracy: A tool for indoctrination.
124
+ Refutation: Formation of critical citizens.
125
+
126
+ Mass Media
127
+ Conspiracy: Fabricating pro-war consensus.
128
+ Refutation: Plurality of competing voices.
129
+
130
+ Space Exploration
131
+ Conspiracy: A hoax to divert funds.
132
+ Refutation: Science that generates innovation and collaboration.
133
+
134
+ Artificial Intelligence
135
+ Conspiracy: Elites use it to replace humans.
136
+ Refutation: A tool to complement human capabilities.
137
+
138
+ Vaccines
139
+ Conspiracy: A global surveillance program.
140
+ Refutation: Pillars of public health.
141
+
142
+ Pandemics
143
+ Conspiracy: A tool for social control.
144
+ Refutation: Real crises that require coordination.
145
+
146
+ Chemtrails
147
+ Conspiracy: They alter climate and human behavior.
148
+ Refutation: Harmless condensation trails.
149
+
150
+ Extraterrestrials
151
+ Conspiracy: Hidden by governments.
152
+ Refutation: No evidence; scientific skepticism.
153
+
154
+ 5G Technology
155
+ Conspiracy: A mind control weapon.
156
+ Refutation: Safe telecommunications technology.
157
+
158
+ Social Networks
159
+ Conspiracy: Monitoring and shaping opinions.
160
+ Refutation: Spaces for free expression and information.
161
+
162
+ Large Fires
163
+ Conspiracy: Redesigning maps for corporate interests.
164
+ Refutation: Natural and human causes (climate change, negligence).
165
+
166
+ Official History
167
+ Conspiracy: Hides advanced civilizations.
168
+ Refutation: Academic consensus based on archaeological evidence.
169
+
170
+
171
+
172
+ ### Source Data
173
+
174
+ This is an original dataset generated automatically by prompting the DeepSeeker R1 0528 language model.
175
+
176
+ ### Initial Data Collection and Normalization
177
+
178
+ Text samples were generated using carefully designed prompts for 15 pairs of conspiracy topics and their rational counterarguments.
179
+ These prompts were randomly selected during dataset creation to ensure diversity and balance.
180
+ Below are examples of the prompts used to generate the two classes:
181
+
182
+
183
+ #### Conspiratorial prompts (Class 1):
184
+ ["Escríbeme un mensaje tipo tweet conspiranoico sobre cómo las élites financieras controlan los gobiernos mediante deuda.",
185
+
186
+ "Escríbeme un mensaje tipo tweet conspiranoico sobre cómo el cambio climático es una excusa para imponer un gobierno global.",
187
+
188
+ "Escríbeme un mensaje tipo tweet conspiranoico sobre cómo los alimentos procesados están diseñados para reducir la fertilidad.",
189
+
190
+ "Escríbeme un mensaje tipo tweet conspiranoico sobre cómo el sistema educativo está hecho para adoctrinar y no para enseñar.",
191
+
192
+ "Escríbeme un mensaje tipo tweet conspiranoico sobre cómo los medios de comunicación fabrican consensos a favor de la guerra.",
193
+
194
+ "Escríbeme un mensaje tipo tweet conspiranoico sobre cómo la exploración espacial es una farsa para desviar fondos públicos.",
195
+
196
+ "Escríbeme un mensaje tipo tweet conspiranoico sobre cómo la inteligencia artificial está diseñada para reemplazar a los humanos por orden de las élites.",
197
+
198
+ "Escríbeme un mensaje tipo tweet conspiranoico sobre cómo las vacunas forman parte de un programa de vigilancia global.",
199
+
200
+ "Escríbeme un mensaje tipo tweet conspiranoico sobre cómo los gobiernos usan las pandemias como herramienta de control social.",
201
+
202
+ "Escríbeme un mensaje tipo tweet conspiranoico sobre cómo los chemtrails alteran el comportamiento humano y afectan el clima.",
203
+
204
+ "Escríbeme un mensaje tipo tweet conspiranoico sobre cómo los extraterrestres ya están entre nosotros pero los gobiernos lo ocultan.",
205
+
206
+ "Escríbeme un mensaje tipo tweet conspiranoico sobre cómo la tecnología 5G puede usarse como arma de manipulación mental.",
207
+
208
+ "Escríbeme un mensaje tipo tweet conspiranoico sobre cómo las redes sociales están diseñadas para vigilar y moldear opiniones.",
209
+
210
+ "Escríbeme un mensaje tipo tweet conspiranoico sobre cómo los grandes incendios son usados para rediseñar mapas urbanos según intereses corporativos.",
211
+
212
+ "Escríbeme un mensaje tipo tweet conspiranoico sobre cómo la historia oficial ha sido manipulada para esconder civilizaciones avanzadas del pasado."]
213
+
214
+ #### Rational/refuting prompts (Class 0):
215
+ [
216
+ "Escríbeme un mensaje tipo tweet que explique por qué las élites financieras no controlan los gobiernos mediante deuda, sino a través de procesos económicos complejos y transparentes.",
217
+
218
+ "Escríbeme un mensaje tipo tweet que refute la idea de que el cambio climático es una excusa para un gobierno global, y explique por qué es un fenómeno científico real y urgente.",
219
+
220
+ "Escríbeme un mensaje tipo tweet que desmienta que los alimentos procesados están diseñados para reducir la fertilidad, y defienda la seguridad alimentaria regulada por agencias internacionales.",
221
+
222
+ "Escríbeme un mensaje tipo tweet que argumente que el sistema educativo no busca adoctrinar, sino formar ciudadanos críticos y preparados para el mundo real.",
223
+
224
+ "Escríbeme un mensaje tipo tweet que explique que los medios de comunicación no fabrican consensos a favor de la guerra, sino que existen múltiples voces y líneas editoriales en competencia.",
225
+
226
+ "Escríbeme un mensaje tipo tweet que defienda que la exploración espacial no es una farsa, sino un campo científico real que genera innovación, conocimiento y colaboración internacional.",
227
+
228
+ "Escríbeme un mensaje tipo tweet que critique la idea de que la inteligencia artificial está diseñada por las élites para reemplazar a los humanos, y explique cómo puede complementar nuestras capacidades.",
229
+
230
+ "Escríbeme un mensaje tipo tweet que desmienta que las vacunas formen parte de un programa de vigilancia global, y reafirme su importancia para la salud pública.",
231
+
232
+ "Escríbeme un mensaje tipo tweet que explique por qué las pandemias no son herramientas de control social, sino crisis reales que requieren coordinación global para ser contenidas.",
233
+
234
+ "Escríbeme un mensaje tipo tweet que refute la idea de que los chemtrails alteran el comportamiento humano o el clima, y explique qué son en realidad las estelas de los aviones.",
235
+
236
+ "Escríbeme un mensaje tipo tweet que cuestione la idea de que los extraterrestres ya están entre nosotros y que los gobiernos lo ocultan, y promueva el escepticismo científico.",
237
+
238
+ "Escríbeme un mensaje tipo tweet que critique la teoría de que la tecnología 5G puede usarse como arma de manipulación mental, y explique cómo funciona realmente esta tecnología.",
239
+
240
+ "Escríbeme un mensaje tipo tweet que defienda que las redes sociales no están diseñadas únicamente para vigilar o manipular opiniones, sino que también permiten la libre expresión y el acceso a información.",
241
+
242
+ "Escríbeme un mensaje tipo tweet que refute la idea de que los grandes incendios son parte de un plan para rediseñar mapas urbanos, y explique las causas reales detrás de estos desastres.",
243
+
244
+ "Escríbeme un mensaje tipo tweet que explique por qué la historia oficial no está manipulada para esconder civilizaciones avanzadas, y cómo funciona el consenso académico basado en evidencia."
245
+ ]
246
+
247
+
248
+ data = {
249
+ "model": "deepseek/deepseek-r1-0528:free",
250
+
251
+ "messages": [
252
+
253
+ #for rational
254
+ {"role": "system", "content": "Eres un generador de contenido que redacta mensajes tipo tweet con tono racional, escéptico y basado en hechos. Los mensajes deben parecer escritos por personas comunes que valoran el pensamiento crítico y la información verificada. Usa un lenguaje claro y accesible, sin tecnicismos excesivos. Genera cada tweet con una longitud media de 20-30 tokens. Es extremadamente importante que NO incluyas nada más en tu respuesta, escribe solamente el texto que te solicita sin ninguna aclaración o número de tokens."},
255
+ #for conspiranoic
256
+ {"role": "system", "content": "Eres un generador de contenido que redacta mensajes tipo tweet desde una perspectiva conspirativa. Los mensajes deben parecer escritos por alguien que cree sinceramente en lo que dice. Usa un tono serio, alarmista o revelador. El lenguaje debe ser informal, pero con convicción. Cubre cualquier tema conspiranoico (vacunas, política internacional, control social, aliens, etc.). Genera cada tweet con una longitud media de 20 tokens. No incluyas nada más en la salida, solo el texto del tweet."},
257
+ {"role": "user", "content": PROMPTS}
258
+ ],
259
+ "temperature": 1,
260
+ "max_tokens": 512
261
+ }
262
+
263
+
264
+ ### Who Are the Source Language Producers?
265
+
266
+ All text was machine-generated by the DeepSeeker R1 0528 model; no human-generated text is included.
267
+
268
+ ### Annotations
269
+
270
+ #### Annotation Process
271
+
272
+ Labels were automatically assigned based on the prompt type: conspiratorial messages received label `1`; rational/refuting messages received label `0`.
273
+
274
+ #### Who Are the Annotators?
275
+
276
+ Annotations were generated automatically; no manual annotation was performed.
277
+
278
+ ### Personal and Sensitive Information
279
+
280
+ No personal data is included. The dataset consists solely of synthetic, topic-based short texts.
281
+
282
+ ## Considerations for Using the Data
283
+
284
+ ### Social Impact of Dataset
285
+
286
+ This dataset can help develop tools to detect conspiracy theories and misinformation in Spanish text. However, care should be taken to avoid misuse or stigmatization of legitimate critical thinking.
287
+
288
+ ### Discussion of Biases
289
+
290
+ - The dataset may contain biases originating from the language model used for generation.
291
+ - The binary label scheme simplifies complex social views.
292
+ - Stylistic biases related to prompt engineering may be present.
293
+
294
+ ### Other Known Limitations
295
+
296
+ - Fully synthetic; does not reflect real human language or discourse nuance.
297
+ - Limited to 15 predefined topics.
298
+ - May not generalize to other languages or domains.
299
+
300
+ ## Additional Information
301
+
302
+ ### Dataset Curators
303
+
304
+ Created by [MorcuendeA].
305
+
306
+ ### Licensing Information
307
+
308
+ This dataset is licensed under the Creative Commons Attribution 4.0 International (CC BY 4.0) license.
309
+
310
+ ### Citation Information
311
+
312
+ If you use this dataset, please cite as:
313
+
314
+ @misc{conspiratextes2025,
315
+ title = {ConspiraText-ES: A Synthetic Spanish Dataset of Conspiratorial and Rational Statements},
316
+ author = {Morcuende A},
317
+ year = {2025},
318
+ howpublished = {\url{https://huggingface.co/datasets/MorcuendeA/ConspiraText-ES}},
319
+ note = {Synthetic dataset created using DeepSeeker R1 0528}
320
+ }
321