MARTINI_enrich_BERTopic_Middle_East_Spectator
This is a BERTopic model. BERTopic is a flexible and modular topic modeling framework that allows for the generation of easily interpretable topics from large datasets.
Usage
To use this model, please install BERTopic:
pip install -U bertopic
You can use the model as follows:
from bertopic import BERTopic
topic_model = BERTopic.load("AIDA-UPM/MARTINI_enrich_BERTopic_Middle_East_Spectator")
topic_model.get_topic_info()
Topic overview
- Number of topics: 34
- Number of training documents: 3345
Click here for an overview of all topics.
| Topic ID | Topic Keywords | Topic Frequency | Label |
|---|---|---|---|
| -1 | hezbollah - khamenei - gaza - jerusalem - missiles | 20 | -1_hezbollah_khamenei_gaza_jerusalem |
| 0 | iraqi - assad - airstrikes - faction - ismael | 1543 | 0_iraqi_assad_airstrikes_faction |
| 1 | palestine - nasrallah - jihad - martyrs - victory | 194 | 1_palestine_nasrallah_jihad_martyrs |
| 2 | channel - news - subscribers - censored - unbiased | 166 | 2_channel_news_subscribers_censored |
| 3 | gaza - israelis - egyptians - suez - libyan | 126 | 3_gaza_israelis_egyptians_suez |
| 4 | netanyahu - hezbollah - galilee - yoav - threatens | 103 | 4_netanyahu_hezbollah_galilee_yoav |
| 5 | karabakh - nakhchivan - azerbaijani - armenians - yerevan | 98 | 5_karabakh_nakhchivan_azerbaijani_armenians |
| 6 | yemen - warship - missiles - maersk - gulf | 92 | 6_yemen_warship_missiles_maersk |
| 7 | saudi - khamenei - bahrain - faisal - zayed | 86 | 7_saudi_khamenei_bahrain_faisal |
| 8 | gaza - civilians - bombed - younis - tunnels | 83 | 8_gaza_civilians_bombed_younis |
| 9 | iran - abdollahian - ambassador - doha - sanctioned | 74 | 9_iran_abdollahian_ambassador_doha |
| 10 | missiles - iran - hypersonic - baikonur - launched | 69 | 10_missiles_iran_hypersonic_baikonur |
| 11 | kadyrov - voronezh - gerasimov - regiment - massacre | 54 | 11_kadyrov_voronezh_gerasimov_regiment |
| 12 | hezbollah - drone - haifa - launched - zabdin | 47 | 12_hezbollah_drone_haifa_launched |
| 13 | soleimani - mousavi - terrorists - damascus - martyred | 44 | 13_soleimani_mousavi_terrorists_damascus |
| 14 | iranians - hamedan - allahu - كير - الاحرار | 43 | 14_iranians_hamedan_allahu_كير |
| 15 | hezbollah - khirbet - ramyeh - ambush - sites | 41 | 15_hezbollah_khirbet_ramyeh_ambush |
| 16 | sukhoi - drone - turbojet - squadrons - tatarstan | 35 | 16_sukhoi_drone_turbojet_squadrons |
| 17 | belgorod - zaporizhia - volodymyr - sevastopol - reinforcements | 33 | 17_belgorod_zaporizhia_volodymyr_sevastopol |
| 18 | hezbollah - mujahid - hassan - haidar - martyrs | 31 | 18_hezbollah_mujahid_hassan_haidar |
| 19 | gaza - airstrikes - ashkelon - merkava - update | 31 | 19_gaza_airstrikes_ashkelon_merkava |
| 20 | biden - netanyahu - cnn - ayatollahs - interviewed | 31 | 20_biden_netanyahu_cnn_ayatollahs |
| 21 | jew - אילן - kanye - musk - goddamn | 28 | 21_jew_אילן_kanye_musk |
| 22 | khuzestan - khorramabad - taliban - armored - irgc | 28 | 22_khuzestan_khorramabad_taliban_armored |
| 23 | intifada - qassam - hamza - spokesman - obeida | 28 | 23_intifada_qassam_hamza_spokesman |
| 24 | iran - balochistan - terrorists - chabahar - mashhad | 27 | 24_iran_balochistan_terrorists_chabahar |
| 25 | iran - nuclear - cnn - retaliate - notified | 26 | 25_iran_nuclear_cnn_retaliate |
| 26 | hezbollah - katyusha - missiles - barrage - baalbek | 26 | 26_hezbollah_katyusha_missiles_barrage |
| 27 | donald - democrats - newsom - ballot - dumbest | 25 | 27_donald_democrats_newsom_ballot |
| 28 | lebanon - gunfire - outposts - idf - tanks | 24 | 28_lebanon_gunfire_outposts_idf |
| 29 | russia - attackers - bryansk - kiev - terrorist | 24 | 29_russia_attackers_bryansk_kiev |
| 30 | hormuz - tankers - strait - submarine - seized | 23 | 30_hormuz_tankers_strait_submarine |
| 31 | gaza - donate - inshaallah - subscribers - delivered | 21 | 31_gaza_donate_inshaallah_subscribers |
| 32 | palestinian - ashkelon - gunfights - infiltrators - rohovot | 21 | 32_palestinian_ashkelon_gunfights_infiltrators |
Training hyperparameters
- calculate_probabilities: True
- language: None
- low_memory: False
- min_topic_size: 10
- n_gram_range: (1, 1)
- nr_topics: None
- seed_topic_list: None
- top_n_words: 10
- verbose: False
- zeroshot_min_similarity: 0.7
- zeroshot_topic_list: None
Framework versions
- Numpy: 1.26.4
- HDBSCAN: 0.8.40
- UMAP: 0.5.7
- Pandas: 2.2.3
- Scikit-Learn: 1.5.2
- Sentence-transformers: 3.3.1
- Transformers: 4.46.3
- Numba: 0.60.0
- Plotly: 5.24.1
- Python: 3.10.12
- Downloads last month
- -