ShivamSrng
commited on
Commit
•
ec07943
1
Parent(s):
d024b5b
Fine-tuned Topic Model for aspects_to_improve column
Browse files- README.md +147 -0
- config.json +16 -0
- ctfidf.safetensors +3 -0
- ctfidf_config.json +0 -0
- topic_embeddings.safetensors +3 -0
- topics.json +0 -0
README.md
ADDED
@@ -0,0 +1,147 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
|
2 |
+
---
|
3 |
+
tags:
|
4 |
+
- bertopic
|
5 |
+
library_name: bertopic
|
6 |
+
pipeline_tag: text-classification
|
7 |
+
---
|
8 |
+
|
9 |
+
# after_covid_distance_learning_aspects_to_improve
|
10 |
+
|
11 |
+
This is a [BERTopic](https://github.com/MaartenGr/BERTopic) model.
|
12 |
+
BERTopic is a flexible and modular topic modeling framework that allows for the generation of easily interpretable topics from large datasets.
|
13 |
+
|
14 |
+
## Usage
|
15 |
+
|
16 |
+
To use this model, please install BERTopic:
|
17 |
+
|
18 |
+
```
|
19 |
+
pip install -U bertopic
|
20 |
+
```
|
21 |
+
|
22 |
+
You can use the model as follows:
|
23 |
+
|
24 |
+
```python
|
25 |
+
from bertopic import BERTopic
|
26 |
+
topic_model = BERTopic.load("ShivamSrng/after_covid_distance_learning_aspects_to_improve")
|
27 |
+
|
28 |
+
topic_model.get_topic_info()
|
29 |
+
```
|
30 |
+
|
31 |
+
## Topic overview
|
32 |
+
|
33 |
+
* Number of topics: 78
|
34 |
+
* Number of training documents: 5706
|
35 |
+
|
36 |
+
<details>
|
37 |
+
<summary>Click here for an overview of all topics.</summary>
|
38 |
+
|
39 |
+
| Topic ID | Topic Keywords | Topic Frequency | Label |
|
40 |
+
|----------|----------------|-----------------|-------|
|
41 |
+
| 0 | video lectures - assignments - lecture videos - lectures - classes | 3789 | 0_video lectures_assignments_lecture videos_lectures |
|
42 |
+
| 1 | group projects class - group project aspect - group projects - instead group projects - group project | 148 | 1_group projects class_group project aspect_group projects_instead group projects |
|
43 |
+
| 2 | semester large project end - large project end semester - think eliminating final project - project smaller assignments semester - semester large project | 143 | 2_semester large project end_large project end semester_think eliminating final project_project smaller assignments semester |
|
44 |
+
| 3 | discussion posts - post said discussions need - discussion post - post said discussions - posts assignments discussion posts | 78 | 3_discussion posts_post said discussions need_discussion post_post said discussions |
|
45 |
+
| 4 | purchase textbook - pricey textbooks students - pricey textbooks students need - pricey textbooks - textbook | 43 | 4_purchase textbook_pricey textbooks students_pricey textbooks students need_pricey textbooks |
|
46 |
+
| 5 | multi linear regression error - overkill expect pulled way - leeched despite trying - leeched despite trying kids - multi linear regression | 40 | 5_multi linear regression error_overkill expect pulled way_leeched despite trying_leeched despite trying kids |
|
47 |
+
| 6 | read week studying chapters - reading chapters - reading chapters textbook - read annotate study chapters - material taught chapter onwards | 39 | 6_read week studying chapters_reading chapters_reading chapters textbook_read annotate study chapters |
|
48 |
+
| 7 | recorded videos maybe updated - recorded mistakes video content - revision including videos videos - revision including videos - record everything videos better | 39 | 7_recorded videos maybe updated_recorded mistakes video content_revision including videos videos_revision including videos |
|
49 |
+
| 8 | instructions posted severely lacking - better instructions - instructions tutorials - instructions tutorials instruction - instructions working | 39 | 8_instructions posted severely lacking_better instructions_instructions tutorials_instructions tutorials instruction |
|
50 |
+
| 9 | quality lectures audio - quality lectures suspect sound - quality lectures audio quality - quality lecture videos audio - recorded lectures old audio | 38 | 9_quality lectures audio_quality lectures suspect sound_quality lectures audio quality_quality lecture videos audio |
|
51 |
+
| 10 | potential applications empowering - new technology programming sense - new technology programming - practical insights applications deeper - responsibility learn new technology | 38 | 10_potential applications empowering_new technology programming sense_new technology programming_practical insights applications deeper |
|
52 |
+
| 11 | maybe extra credit homework - operations mncs - maybe extra credit - price sold units reason - purpose original explanation | 35 | 11_maybe extra credit homework_operations mncs_maybe extra credit_price sold units reason |
|
53 |
+
| 12 | think improvements required - improvements needs - think improvements needed - think improvements required aspects - improvements needed | 34 | 12_think improvements required_improvements needs_think improvements needed_think improvements required aspects |
|
54 |
+
| 13 | quite confusing material - overwhelming hard comprehend virtually - limited text difficult understand - overwhelming hard comprehend - questions clear confused materials | 33 | 13_quite confusing material_overwhelming hard comprehend virtually_limited text difficult understand_overwhelming hard comprehend |
|
55 |
+
| 14 | technical writing - little readings having essay - writing think need - little content focus topic - paper advance helpful | 33 | 14_technical writing_little readings having essay_writing think need_little content focus topic |
|
56 |
+
| 15 | remember alot information - memorize exams likely - remember alot - memorize exams - memorize exams likely look | 31 | 15_remember alot information_memorize exams likely_remember alot_memorize exams |
|
57 |
+
| 16 | semester let students - semester versus using multiple - semester let students pick - required students inclined - required students inclined complete | 30 | 16_semester let students_semester versus using multiple_semester let students pick_required students inclined |
|
58 |
+
| 17 | technical electives masters civil - level class graduate rutgers - industry contractors classes geared - institution developing future work - industry contractors classes | 29 | 17_technical electives masters civil_level class graduate rutgers_industry contractors classes geared_institution developing future work |
|
59 |
+
| 18 | students workload reasonable work - student taking workload - students workload - needs respectful students workload - student taking workload needs | 28 | 18_students workload reasonable work_student taking workload_students workload_needs respectful students workload |
|
60 |
+
| 19 | organize pacing feels disjointed - organizing everything - organizing everything digitally mins - organized feels material content - organizing everything digitally | 28 | 19_organize pacing feels disjointed_organizing everything_organizing everything digitally mins_organized feels material content |
|
61 |
+
| 20 | programs encourage bad programming - learn provides educational value - mistakes learning - mistakes learning learned school - point students learn learn | 27 | 20_programs encourage bad programming_learn provides educational value_mistakes learning_mistakes learning learned school |
|
62 |
+
| 21 | software install - required software learn - software easily accessible - software - related computer software | 25 | 21_software install_required software learn_software easily accessible_software |
|
63 |
+
| 22 | new technologies include reference - reflect current industry practices - practical regular updates curriculum - recent information supplementary materials - recent developments occasionally | 25 | 22_new technologies include reference_reflect current industry practices_practical regular updates curriculum_recent information supplementary materials |
|
64 |
+
| 23 | labs easy understand - labs easy understand think - labs learned form labs - labs maybe labs involving - labs information | 25 | 23_labs easy understand_labs easy understand think_labs learned form labs_labs maybe labs involving |
|
65 |
+
| 24 | business plan - new business process ideas - offer example assignment rubric - page business plan - new business process | 25 | 24_business plan_new business process ideas_offer example assignment rubric_page business plan |
|
66 |
+
| 25 | practical cases ideas case - practical cases ideas - problems examples ideas projects - maybe real life examples - projects need pratical application | 25 | 25_practical cases ideas case_practical cases ideas_problems examples ideas projects_maybe real life examples |
|
67 |
+
| 26 | proper setups coding project - projects application implemented - projects application - project setting development environment - ide | 24 | 26_proper setups coding project_projects application implemented_projects application_project setting development environment |
|
68 |
+
| 27 | met teacher midterm review - listens students - met teacher midterm - midterm taught gave - listens students concerns | 24 | 27_met teacher midterm review_listens students_met teacher midterm_midterm taught gave |
|
69 |
+
| 28 | raise students awareness ethical - minds students think ethical - ethical analysis - project assignment ethical analyses - understanding biomedical ethics | 24 | 28_raise students awareness ethical_minds students think ethical_ethical analysis_project assignment ethical analyses |
|
70 |
+
| 29 | papers subject developed traffic - lectures provides material - lectures provides material reads - regulations details - lectures provides | 24 | 29_papers subject developed traffic_lectures provides material_lectures provides material reads_regulations details |
|
71 |
+
| 30 | notes internet access online - notes internet access - online section online service - online service costs additional - online mishaps understand | 24 | 30_notes internet access online_notes internet access_online section online service_online service costs additional |
|
72 |
+
| 31 | old material considered outdated - material considered outdated - outdated relevant material outdated - outdated relevant material - old material quite outdated | 23 | 31_old material considered outdated_material considered outdated_outdated relevant material outdated_outdated relevant material |
|
73 |
+
| 32 | way think everything great - think everything great - feel modified great think - think great - way think great | 23 | 32_way think everything great_think everything great_feel modified great think_think great |
|
74 |
+
| 33 | suggestions - suggestions current - recommendations - suggestions think - think suggestions current | 23 | 33_suggestions_suggestions current_recommendations_suggestions think |
|
75 |
+
| 34 | learning materials provided insufficient - educational material provided - material provided learn - learning materials provided - educational material | 23 | 34_learning materials provided insufficient_educational material provided_material provided learn_learning materials provided |
|
76 |
+
| 35 | review week modules - weekly discussions - review week modules posted - materials discussion week repetitive - weekly discussion | 22 | 35_review week modules_weekly discussions_review week modules posted_materials discussion week repetitive |
|
77 |
+
| 36 | quiz times flexible - quiz provided time anticipation - quizzes hour period - quizzes entire week - quizzes entire week instead | 21 | 36_quiz times flexible_quiz provided time anticipation_quizzes hour period_quizzes entire week |
|
78 |
+
| 37 | office hour accommodate - office hours effective way - recommend switch office hours - office hours easy - office hours certain times | 21 | 37_office hour accommodate_office hours effective way_recommend switch office hours_office hours easy |
|
79 |
+
| 38 | maybe concepts involving finances - math frequently focus business - mathematics suited managers using - mathematics suited managers - maybe concepts involving | 21 | 38_maybe concepts involving finances_math frequently focus business_mathematics suited managers using_mathematics suited managers |
|
80 |
+
| 39 | modules informative - modules class modules informative - modules informative wish - maybe split modules instead - maybe split modules | 21 | 39_modules informative_modules class modules informative_modules informative wish_maybe split modules instead |
|
81 |
+
| 40 | programming type helpful videos - little tutorials quake having - little tutorials - little tutorials quake - programmer throw novice youtube | 20 | 40_programming type helpful videos_little tutorials quake having_little tutorials_little tutorials quake |
|
82 |
+
| 41 | learned professor enjoyed - loved hear professor experiences - professor class great - professor enjoyed professor class - loved material professor | 20 | 41_learned professor enjoyed_loved hear professor experiences_professor class great_professor enjoyed professor class |
|
83 |
+
| 42 | poor slides presentations old - slides outdated - slides outdated engaging - slides outdated content - slides need updated | 20 | 42_poor slides presentations old_slides outdated_slides outdated engaging_slides outdated content |
|
84 |
+
| 43 | little detailed explanation formulas - helpful calculating - indepth explanations statistical formulas - formulas - calculating | 19 | 43_little detailed explanation formulas_helpful calculating_indepth explanations statistical formulas_formulas |
|
85 |
+
| 44 | major problem solving - problem solving - midterm work problems provided - major problem solving questions - solving instead | 19 | 44_major problem solving_problem solving_midterm work problems provided_major problem solving questions |
|
86 |
+
| 45 | meant engineers doctoral class - perspective topics related engineering - topics oriented logistics chapters - engineering - meant engineers doctoral | 19 | 45_meant engineers doctoral class_perspective topics related engineering_topics oriented logistics chapters_engineering |
|
87 |
+
| 46 | students posting response answering - student responses students posting - students posting response - student responses students - students saying reply takes | 18 | 46_students posting response answering_student responses students posting_students posting response_student responses students |
|
88 |
+
| 47 | modern cloud - old acceptable cloud computing - modern cloud computing possible - cloud computing - modern cloud computing | 18 | 47_modern cloud_old acceptable cloud computing_modern cloud computing possible_cloud computing |
|
89 |
+
| 48 | using proctoru exams - proctoru exams incredibly annoying - proctoru exams annoying - proctoru different proctoring software - proctoru exams incredibly | 18 | 48_using proctoru exams_proctoru exams incredibly annoying_proctoru exams annoying_proctoru different proctoring software |
|
90 |
+
| 49 | materials need updatingneed revisiting - material applicable lacked - material applicable lacked examples - materials need updatingneed - material posted example | 18 | 49_materials need updatingneed revisiting_material applicable lacked_material applicable lacked examples_materials need updatingneed |
|
91 |
+
| 50 | new databases need exercises - new databases need - programming understand database - databases - rdbms | 16 | 50_new databases need exercises_new databases need_programming understand database_databases |
|
92 |
+
| 51 | risky sensitive info computer - remote control experience - sensitive info computer - feels risky sensitive info - risky sensitive info | 16 | 51_risky sensitive info computer_remote control experience_sensitive info computer_feels risky sensitive info |
|
93 |
+
| 52 | review communication requirements bit - review communication - told receive comments report - report round submission occurred - review communication requirements | 16 | 52_review communication requirements bit_review communication_told receive comments report_report round submission occurred |
|
94 |
+
| 53 | syllabus outlines everything deadlines - syllabus needs - syllabus syllabus outlines everything - making syllabus - syllabus syllabus outlines | 16 | 53_syllabus outlines everything deadlines_syllabus needs_syllabus syllabus outlines everything_making syllabus |
|
95 |
+
| 54 | wrong writing points received - marked wrong writing - mistake example credit - value simple mistake example - mistake example credit correct | 16 | 54_wrong writing points received_marked wrong writing_mistake example credit_value simple mistake example |
|
96 |
+
| 55 | understand exams lockdown browser - think lockdown browser quizzes - lockdown browser quizzes unnecessary - quiz lockdown browser - lockdown browser quizzes | 15 | 55_understand exams lockdown browser_think lockdown browser quizzes_lockdown browser quizzes unnecessary_quiz lockdown browser |
|
97 |
+
| 56 | online face face instead - understand online compared person - offer online sections - online compared person - online compared person prefer | 15 | 56_online face face instead_understand online compared person_offer online sections_online compared person |
|
98 |
+
| 57 | everything great - everything great journey far - great journey far everything - everything thanks professor hanna - everything comment everything great | 14 | 57_everything great_everything great journey far_great journey far everything_everything thanks professor hanna |
|
99 |
+
| 58 | notes present java todays - searching java docs - lecture notes present java - reflect current java developments - present java todays world | 14 | 58_notes present java todays_searching java docs_lecture notes present java_reflect current java developments |
|
100 |
+
| 59 | clearly dated material sufficient - clearly dated material - moodle clearly dated material - mentions moodle clearly dated - sufficient mentions moodle dated | 14 | 59_clearly dated material sufficient_clearly dated material_moodle clearly dated material_mentions moodle clearly dated |
|
101 |
+
| 60 | math hours personally bothered - math hours personally - math focus - math late feel - math hours | 13 | 60_math hours personally bothered_math hours personally_math focus_math late feel |
|
102 |
+
| 61 | everything great need improvement - goodno need improvements everything - improvements everything great need - need improvements everything great - need improvements everything | 12 | 61_everything great need improvement_goodno need improvements everything_improvements everything great need_need improvements everything great |
|
103 |
+
| 62 | recommend having theme - recommend having theme imporvements - future recommend having theme - health safety underground constructions - theme imporvements need | 12 | 62_recommend having theme_recommend having theme imporvements_future recommend having theme_health safety underground constructions |
|
104 |
+
| 63 | yells emailing replies fake - replies fake means say - replies fake means - emailing replies fake means - extreme yells emailing replies | 12 | 63_yells emailing replies fake_replies fake means say_replies fake means_emailing replies fake means |
|
105 |
+
| 64 | using aws - aws - links helpful understand cloud - project python aws - project python aws cloud | 12 | 64_using aws_aws_links helpful understand cloud_project python aws |
|
106 |
+
| 65 | change change wish - lenient life hard change - wish change love change - say change change wish - change | 11 | 65_change change wish_lenient life hard change_wish change love change_say change change wish |
|
107 |
+
| 66 | optional webex sessions students - requiring students meet webex - webex meeting quizzes students - webex meetings useful - optional webex meeting quizzes | 11 | 66_optional webex sessions students_requiring students meet webex_webex meeting quizzes students_webex meetings useful |
|
108 |
+
| 67 | respond students professor time - professor time limit - prepare lesson professor allow - period respond students professor - professor time limit equal | 11 | 67_respond students professor time_professor time limit_prepare lesson professor allow_period respond students professor |
|
109 |
+
| 68 | unclear instructions capsim simulation - nice capsim simulation confusing - simulation capsim - capsim simulation - simulation capsim integration little | 11 | 68_unclear instructions capsim simulation_nice capsim simulation confusing_simulation capsim_capsim simulation |
|
110 |
+
| 69 | professor feedback submitted works - professor feedback - professor feedback provided professor - professor assignments feedback - lack feedback professor | 11 | 69_professor feedback submitted works_professor feedback_professor feedback provided professor_professor assignments feedback |
|
111 |
+
| 70 | networking tools - protocols network security imprtance - want improvements internet layer - using networking tools - network security imprtance | 9 | 70_networking tools_protocols network security imprtance_want improvements internet layer_using networking tools |
|
112 |
+
| 71 | everything - everything alright far - everything alright - far everything - say everything | 9 | 71_everything_everything alright far_everything alright_far everything |
|
113 |
+
| 72 | years old prerecorded videos - videos year old dates - old prerecorded videos - better videos free things - prerecorded videos return illegal | 9 | 72_years old prerecorded videos_videos year old dates_old prerecorded videos_better videos free things |
|
114 |
+
| 73 | need professor professor michael - courses taken professor best - need professor - need professor professor - best courses taken professor | 8 | 73_need professor professor michael_courses taken professor best_need professor_need professor professor |
|
115 |
+
| 74 | online exams closed - online exams closed book - times online exams - set times online exams - hour exam classes | 8 | 74_online exams closed_online exams closed book_times online exams_set times online exams |
|
116 |
+
| 75 | rehire keith williams forgetful - rehire keith williams - better managed rehire keith - williams forgetful - rehire keith | 7 | 75_rehire keith williams forgetful_rehire keith williams_better managed rehire keith_williams forgetful |
|
117 |
+
| 76 | rude received little feedback - emails explanations feedback discussions - received little feedback forum - recieved rude received little - responses recieved rude received | 7 | 76_rude received little feedback_emails explanations feedback discussions_received little feedback forum_recieved rude received little |
|
118 |
+
| 77 | obsolete chat gpt students - students jobs obsolete chat - tell students google chat - chat gpt - students discord | 7 | 77_obsolete chat gpt students_students jobs obsolete chat_tell students google chat_chat gpt |
|
119 |
+
|
120 |
+
</details>
|
121 |
+
|
122 |
+
## Training hyperparameters
|
123 |
+
|
124 |
+
* calculate_probabilities: False
|
125 |
+
* language: None
|
126 |
+
* low_memory: False
|
127 |
+
* min_topic_size: 10
|
128 |
+
* n_gram_range: (1, 1)
|
129 |
+
* nr_topics: auto
|
130 |
+
* seed_topic_list: None
|
131 |
+
* top_n_words: 7
|
132 |
+
* verbose: True
|
133 |
+
* zeroshot_min_similarity: 0.7
|
134 |
+
* zeroshot_topic_list: None
|
135 |
+
|
136 |
+
## Framework versions
|
137 |
+
|
138 |
+
* Numpy: 1.26.4
|
139 |
+
* HDBSCAN: 0.8.39
|
140 |
+
* UMAP: 0.5.7
|
141 |
+
* Pandas: 2.2.3
|
142 |
+
* Scikit-Learn: 1.5.2
|
143 |
+
* Sentence-transformers: 3.2.1
|
144 |
+
* Transformers: 4.46.2
|
145 |
+
* Numba: 0.60.0
|
146 |
+
* Plotly: 5.24.1
|
147 |
+
* Python: 3.10.11
|
config.json
ADDED
@@ -0,0 +1,16 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"calculate_probabilities": false,
|
3 |
+
"language": null,
|
4 |
+
"low_memory": false,
|
5 |
+
"min_topic_size": 10,
|
6 |
+
"n_gram_range": [
|
7 |
+
1,
|
8 |
+
1
|
9 |
+
],
|
10 |
+
"nr_topics": "auto",
|
11 |
+
"seed_topic_list": null,
|
12 |
+
"top_n_words": 7,
|
13 |
+
"verbose": true,
|
14 |
+
"zeroshot_min_similarity": 0.7,
|
15 |
+
"zeroshot_topic_list": null
|
16 |
+
}
|
ctfidf.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:baaab8d37dd6f809e5f02c57f5ca8a9ab50f0ea0d8f9bcd0bee2bfc560a02036
|
3 |
+
size 2146076
|
ctfidf_config.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|
topic_embeddings.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:fdf1af2d504c931154ea9a388b9219568226d0bc44024a305f5f54298d093dd7
|
3 |
+
size 239704
|
topics.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|