cnn_dailymail_108_3000_1500_train

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("KingKazma/cnn_dailymail_108_3000_1500_train")

topic_model.get_topic_info()

Topic overview

• Number of topics: 51
• Number of training documents: 3000

Click here for an overview of all topics.

Topic ID	Topic Keywords	Topic Frequency	Label
-1	said - one - people - year - would	10	-1_said_one_people_year
0	league - player - cup - club - game	954	0_league_player_cup_club
1	police - said - court - told - murder	308	1_police_said_court_told
2	dog - animal - cat - elephant - zoo	290	2_dog_animal_cat_elephant
3	mr - minister - labour - cameron - prime	113	3_mr_minister_labour_cameron
4	obama - clinton - president - republican - campaign	104	4_obama_clinton_president_republican
5	school - teacher - student - nfl - said	84	5_school_teacher_student_nfl
6	food - milk - drink - wine - bottle	72	6_food_milk_drink_wine
7	flight - plane - passenger - pilot - aircraft	49	7_flight_plane_passenger_pilot
8	user - facebook - google - ipad - device	48	8_user_facebook_google_ipad
9	olympic - gold - race - games - medal	46	9_olympic_gold_race_games
10	doll - dress - fashion - look - style	44	10_doll_dress_fashion_look
11	afghan - afghanistan - taliban - military - pakistan	43	11_afghan_afghanistan_taliban_military
12	transplant - patient - heart - hospital - cancer	42	12_transplant_patient_heart_hospital
13	iran - syrian - said - president - egypt	42	13_iran_syrian_said_president
14	show - film - million - like - movie	39	14_show_film_million_like
15	property - house - price - home - apartment	38	15_property_house_price_home
16	earth - asteroid - moon - volcano - planet	34	16_earth_asteroid_moon_volcano
17	federer - djokovic - match - murray - seed	33	17_federer_djokovic_match_murray
18	jackson - jacksons - album - song - music	31	18_jackson_jacksons_album_song
19	ship - boat - coast - said - vessel	30	19_ship_boat_coast_said
20	russia - russian - putin - ukraine - moscow	30	20_russia_russian_putin_ukraine
21	snow - weather - temperature - climate - water	29	21_snow_weather_temperature_climate
22	police - station - mr - man - gang	28	22_police_station_mr_man
23	ebola - disease - vaccine - virus - health	28	23_ebola_disease_vaccine_virus
24	weight - fat - diet - burn - exercise	28	24_weight_fat_diet_burn
25	syria - isis - islamic - muslims - alqudsi	23	25_syria_isis_islamic_muslims
26	boko - haram - nigeria - nigerian - turkana	23	26_boko_haram_nigeria_nigerian
27	korea - north - korean - kim - pyongyang	22	27_korea_north_korean_kim
28	driver - driving - road - car - speed	22	28_driver_driving_road_car
29	school - child - education - internet - english	21	29_school_child_education_internet
30	mcilroy - woods - pga - tournament - round	20	30_mcilroy_woods_pga_tournament
31	race - car - driver - team - f1	19	31_race_car_driver_team
32	princess - prince - diana - royal - palace	18	32_princess_prince_diana_royal
33	climbing - climb - mountain - everest - ang	18	33_climbing_climb_mountain_everest
34	wedding - bieber - couple - together - love	18	34_wedding_bieber_couple_together
35	nhs - care - patient - hospital - health	17	35_nhs_care_patient_hospital
36	iraq - iraqi - isis - baghdad - kurdish	16	36_iraq_iraqi_isis_baghdad
37	cartel - drug - mexican - mexico - crack	15	37_cartel_drug_mexican_mexico
38	painting - picasso - art - artist - gogh	15	38_painting_picasso_art_artist
39	castro - zelaya - fidel - micheletti - president	14	39_castro_zelaya_fidel_micheletti
40	french - ford - traveller - southampton - taxi	14	40_french_ford_traveller_southampton
41	fire - florissant - bell - firefighter - burned	14	41_fire_florissant_bell_firefighter
42	fight - ali - heavyweight - pacquiao - title	13	42_fight_ali_heavyweight_pacquiao
43	fish - sea - jellyfish - manta - swell	13	43_fish_sea_jellyfish_manta
44	pope - francis - vatican - falkland - islands	12	44_pope_francis_vatican_falkland
45	gay - samesex - lgbt - marriage - state	12	45_gay_samesex_lgbt_marriage
46	castle - tower - building - brent - lego	12	46_castle_tower_building_brent
47	chinese - china - xinhua - chinas - communist	12	47_chinese_china_xinhua_chinas
48	delivery - customer - market - vacuum - coin	10	48_delivery_customer_market_vacuum
49	water - rain - storm - flooding - methane	10	49_water_rain_storm_flooding

Training hyperparameters

• calculate_probabilities: True
• language: english
• 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

Framework versions

• Numpy: 1.22.4
• HDBSCAN: 0.8.33
• UMAP: 0.5.3
• Pandas: 1.5.3
• Scikit-Learn: 1.2.2
• Sentence-transformers: 2.2.2
• Transformers: 4.31.0
• Numba: 0.56.4
• Plotly: 5.13.1
• Python: 3.10.6