BERTopic_Economic

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("karinegabsschon/BERTopic_Economic")

topic_model.get_topic_info()

Topic overview

• Number of topics: 37
• Number of training documents: 1290

Click here for an overview of all topics.

Topic ID	Topic Keywords	Topic Frequency	Label
-1	electric - car - cars - vehicles - new	10	-1_electric_car_cars_vehicles
0	byd - chinese - china - market - electric	249	0_byd_chinese_china_market
1	tesla - sales - musk - year - europe	131	1_tesla_sales_musk_year
2	new - used - year - car - month	86	2_new_used_year_car
3	rivian - motley - motley fool - fool - stocks	55	3_rivian_motley_motley fool_fool
4	charging - charging points - points - stations - charging stations	52	4_charging_charging points_points_stations
5	tesla - musk - trump - elon - elon musk	45	5_tesla_musk_trump_elon
6	spain - electric - moves - ebro - plan	38	6_spain_electric_moves_ebro
7	charging - czech - ev charging - slovakia - czech republic	37	7_charging_czech_ev charging_slovakia
8	units - ukraine - used - region - vehicles	33	8_units_ukraine_used_region
9	tesla - musk - gerber - tsla - elon	33	9_tesla_musk_gerber_tsla
10	hyundai - billion - honda - plant - nissan	32	10_hyundai_billion_honda_plant
11	tax - car - pay - car tax - drivers	31	11_tax_car_pay_car tax
12	percent - cars - previous year - registrations - previous	30	12_percent_cars_previous year_registrations
13	million - iea - sales - global - electric	29	13_million_iea_sales_global
14	cars - tax - purchase - federal - government	29	14_cars_tax_purchase_federal
15	xiaomi - nio - li - chinese - yu7	28	15_xiaomi_nio_li_chinese
16	quarter - tesla - sales - electric vehicle - gm	26	16_quarter_tesla_sales_electric vehicle
17	volvo - audi - jobs - cent - company	23	17_volvo_audi_jobs_cent
18	public - charging - uk - charge - ev	23	18_public_charging_uk_charge
19	discounts - combustion - dudenhöffer - cars - prices	23	19_discounts_combustion_dudenhöffer_cars
20	euros - electric - french - aid - energy	22	20_euros_electric_french_aid
21	china - shanghai - chinese - market - car	22	21_china_shanghai_chinese_market
22	id - vw - every1 - id every1 - 000 euros	19	22_id_vw_every1_id every1
23	ferrari - stellantis - italy - elkann - october	17	23_ferrari_stellantis_italy_elkann
24	foxconn - mitsubishi - japanese - nissan - mitsubishi motors	17	24_foxconn_mitsubishi_japanese_nissan
25	belarus - charging - stations - electric - electric charging	16	25_belarus_charging_stations_electric
26	volkswagen - europe - vw - group - percent	16	26_volkswagen_europe_vw_group
27	german - vw - market - group - percent	15	27_german_vw_market_group
28	used - used car - cars - percent - autoscout24	15	28_used_used car_cars_percent
29	vinfast - vf - vietnamese - vinfast auto - quarter	14	29_vinfast_vf_vietnamese_vinfast auto
30	drivers - home - ev - petrol - charging	13	30_drivers_home_ev_petrol
31	uk - car - government - mandate - evs	13	31_uk_car_government_mandate
32	pod - pod point - point - edf - charging	13	32_pod_pod point_point_edf
33	india - tata - ev - tata motors - plans	12	33_india_tata_ev_tata motors
34	russia - electric - sales - passenger - voyah	12	34_russia_electric_sales_passenger
35	analysts - gm - energy - general motors - general	11	35_analysts_gm_energy_general motors

Training hyperparameters

• calculate_probabilities: False
• 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: True
• zeroshot_min_similarity: 0.7
• zeroshot_topic_list: None

Framework versions

• Numpy: 2.0.2
• HDBSCAN: 0.8.40
• UMAP: 0.5.8
• Pandas: 2.2.2
• Scikit-Learn: 1.6.1
• Sentence-transformers: 4.1.0
• Transformers: 4.53.0
• Numba: 0.60.0
• Plotly: 5.24.1
• Python: 3.11.13