parliament_topic_model

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("daniel-023/parliament_topic_model")

topic_model.get_topic_info()

Topic overview

• Number of topics: 20
• Number of training documents: 2005

Click here for an overview of all topics.

Topic ID	Topic Keywords	Topic Frequency	Label
-1	minister - singapore - member - time - government	16	-1_minister_singapore_member_time
0	education - teachers - schools - school - minister	541	0_education_teachers_schools_school
1	water - reclamation - land - development - minister	210	1_water_reclamation_land_development
2	million - singapore - government - finance - year	202	2_million_singapore_government_finance
3	service - police - national - minister - officers	187	3_service_police_national_minister
4	law - council - house - members - committee	140	4_law_council_house_members
5	singapore - identity - citizenship - minister - cards	112	5_singapore_identity_citizenship_minister
6	bus - buses - taxis - transport - taxi	88	6_bus_buses_taxis_transport
7	property - land - tax - board - flats	81	7_property_land_tax_board
8	farmers - prices - minister - price - production	79	8_farmers_prices_minister_price
9	singapore - people - countries - government - foreign	70	9_singapore_people_countries_government
10	culture - cultural - programmes - films - people	49	10_culture_cultural_programmes_films
11	abortion - abortions - family - medical - women	48	11_abortion_abortions_family_medical
12	fund - pension - citizenship - age - years	38	12_fund_pension_citizenship_age
13	airport - telephone - passengers - singapore - terminal	37	13_airport_telephone_passengers_singapore
14	sports - games - national - singapore - national sports	29	14_sports_games_national_singapore
15	drug - drugs - medicines - advertisements - medical	24	15_drug_drugs_medicines_advertisements
16	health - mosquitoes - mosquito - hawkers - rubbish	20	16_health_mosquitoes_mosquito_hawkers
17	brigade - sports - minister - station - firefighting	17	17_brigade_sports_minister_station
18	hawkers - market - hawker - stalls - markets	17	18_hawkers_market_hawker_stalls

Training hyperparameters

• calculate_probabilities: False
• language: english
• low_memory: False
• min_topic_size: 10
• n_gram_range: (1, 1)
• nr_topics: 20
• 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: 0.8.37
• UMAP: 0.5.5
• Pandas: 2.2.0
• Scikit-Learn: 1.4.1.post1
• Sentence-transformers: 2.4.0
• Transformers: 4.43.3
• Numba: 0.60.0
• Plotly: 5.23.0
• Python: 3.12.1