ShivamSrng
commited on
Commit
•
6823b0a
1
Parent(s):
db8f588
Fine-tuned Topic Model for instructor_comments column
Browse files- README.md +139 -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 +1,139 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
|
2 |
+
---
|
3 |
+
tags:
|
4 |
+
- bertopic
|
5 |
+
library_name: bertopic
|
6 |
+
pipeline_tag: text-classification
|
7 |
+
---
|
8 |
+
|
9 |
+
# before_covid_distance_learning_instructor_comments
|
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/before_covid_distance_learning_instructor_comments")
|
27 |
+
|
28 |
+
topic_model.get_topic_info()
|
29 |
+
```
|
30 |
+
|
31 |
+
## Topic overview
|
32 |
+
|
33 |
+
* Number of topics: 70
|
34 |
+
* Number of training documents: 12273
|
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 | lecture - lectures - online class - professors - classes | 8743 | 0_lecture_lectures_online class_professors |
|
42 |
+
| 1 | online instructors faculty - opinion professors encountered - far best professors - best instructors - responsive instructors | 157 | 1_online instructors faculty_opinion professors encountered_far best professors_best instructors |
|
43 |
+
| 2 | gremlin - pick gremlin - plane cute gremlin - plane cute gremlin catch - pick gremlin plane cute | 148 | 2_gremlin_pick gremlin_plane cute gremlin_plane cute gremlin catch |
|
44 |
+
| 3 | project quality - project constitutes final - project prepared class project - project exam - project exam details | 83 | 3_project quality_project constitutes final_project prepared class project_project exam |
|
45 |
+
| 4 | moodle syllabus - moodle assignments - moodle students benefit - moodle quizzes improvement needed - assignments moodle | 82 | 4_moodle syllabus_moodle assignments_moodle students benefit_moodle quizzes improvement needed |
|
46 |
+
| 5 | thank great semester thank - respect thank great semester - thank great semester thanks - thank great semester - semester truly appreciate class | 73 | 5_thank great semester thank_respect thank great semester_thank great semester thanks_thank great semester |
|
47 |
+
| 6 | person class wish teach - matts class future - pick matts class future - offer classes want teacher - matts class future definetly | 71 | 6_person class wish teach_matts class future_pick matts class future_offer classes want teacher |
|
48 |
+
| 7 | material peofessor eric organized - material extremely knowledgeable craft - motivated work knows material - knows material - outstanding knows history | 68 | 7_material peofessor eric organized_material extremely knowledgeable craft_motivated work knows material_knows material |
|
49 |
+
| 8 | questions appreciated took time - providing thought provoking discussion - questions appreciated took - providing thought provoking - provoking discussion exercises study | 68 | 8_questions appreciated took time_providing thought provoking discussion_questions appreciated took_providing thought provoking |
|
50 |
+
| 9 | programming problems unnecessary - programming problems unnecessary ta - problems unnecessary - problems rely self resources - reconfiguring environment seek remedies | 67 | 9_programming problems unnecessary_programming problems unnecessary ta_problems unnecessary_problems rely self resources |
|
51 |
+
| 10 | resource writing lab reports - resource help coding - resource help coding important - project tutorials great question - provided guidance java | 67 | 10_resource writing lab reports_resource help coding_resource help coding important_project tutorials great question |
|
52 |
+
| 11 | pitiful communication awful reply - responds emails - respond emails - misreads email - mute fact rude emailing | 66 | 11_pitiful communication awful reply_responds emails_respond emails_misreads email |
|
53 |
+
| 12 | subject deep programming assignments - concepts programming - video lectures focused concepts - programming assignments - lectures focused concepts | 65 | 12_subject deep programming assignments_concepts programming_video lectures focused concepts_programming assignments |
|
54 |
+
| 13 | unbelievably disorganized idea properly - unbelievably disorganized idea - poorly told wrong improved - poorly told wrong - unable communicate clearly | 65 | 13_unbelievably disorganized idea properly_unbelievably disorganized idea_poorly told wrong improved_poorly told wrong |
|
55 |
+
| 14 | moodle students - class moodle offered - classes moodle - questions moodle students questions - posted moodle teach moodle | 63 | 14_moodle students_class moodle offered_classes moodle_questions moodle students questions |
|
56 |
+
| 15 | powerpoint lectures - slides powerpoint lectures - professors lectures powerpoint informative - powerpoints professors lectures - taught using power point | 62 | 15_powerpoint lectures_slides powerpoint lectures_professors lectures powerpoint informative_powerpoints professors lectures |
|
57 |
+
| 16 | questions communicates everything expects - questions communicates - questions communicates everything - said gets advice precise - properly answer questions want | 61 | 16_questions communicates everything expects_questions communicates_questions communicates everything_said gets advice precise |
|
58 |
+
| 17 | interesting challenging everything - interesting challenging everything good - challenging - learned aside - great disappointed thoroughly enjoyed | 60 | 17_interesting challenging everything_interesting challenging everything good_challenging_learned aside |
|
59 |
+
| 18 | discussion forum - discussion forums - online discuss forums - discussion posts - online discussion boards | 59 | 18_discussion forum_discussion forums_online discuss forums_discussion posts |
|
60 |
+
| 19 | knowledge allows students - knowledge allows students struggling - motivation help students think - motivates improve student evey - life enhance learning | 59 | 19_knowledge allows students_knowledge allows students struggling_motivation help students think_motivates improve student evey |
|
61 |
+
| 20 | learned new things - material graduate learnt things - enjoyed learning - learned project management helped - material learned tremendous | 57 | 20_learned new things_material graduate learnt things_enjoyed learning_learned project management helped |
|
62 |
+
| 21 | classes taken far best - classes taken - best classes - class taken - best classes taken | 57 | 21_classes taken far best_classes taken_best classes_class taken |
|
63 |
+
| 22 | online student need canvas - new canvas platform difficult - canvas page - need canvas updated - online resources canvas | 57 | 22_online student need canvas_new canvas platform difficult_canvas page_need canvas updated |
|
64 |
+
| 23 | online lecture videos - lecture videos - video lectures - video lecture - reading videos material interesting | 57 | 23_online lecture videos_lecture videos_video lectures_video lecture |
|
65 |
+
| 24 | online tutorials thorough assignment - tutorials - online tutorials thorough - instruction - provides examples communicates clearly | 55 | 24_online tutorials thorough assignment_tutorials_online tutorials thorough_instruction |
|
66 |
+
| 25 | method helped learn material - learn material - practice problems instead learning - practice problems instead - opinion help retain learn | 55 | 25_method helped learn material_learn material_practice problems instead learning_practice problems instead |
|
67 |
+
| 26 | periodic interactive sessions semester - online class group work - online class little interaction - student questions - time students read presentations | 55 | 26_periodic interactive sessions semester_online class group work_online class little interaction_student questions |
|
68 |
+
| 27 | puzzling maybe interpret content - interpret content wrong way - interpret content wrong - interpret content - page contradicted information | 51 | 27_puzzling maybe interpret content_interpret content wrong way_interpret content wrong_interpret content |
|
69 |
+
| 28 | wall street journal - reason article - reading dozens irrelevant articles - paper reports felt bombarded - articles | 51 | 28_wall street journal_reason article_reading dozens irrelevant articles_paper reports felt bombarded |
|
70 |
+
| 29 | instructions clear regarding assignments - lacking assignment instructions - assignment instructions - clarify assignments - instructors notes instructions | 50 | 29_instructions clear regarding assignments_lacking assignment instructions_assignment instructions_clarify assignments |
|
71 |
+
| 30 | resulting exam needing rescheduled - second exam - mid term exam - quiz exams blindsided - term exam | 50 | 30_resulting exam needing rescheduled_second exam_mid term exam_quiz exams blindsided |
|
72 |
+
| 31 | paragraph cohesion answer - paragraph cohesion - necessary sufficient paragraph cohesion - paragraph cohesion answer question - phrasal coordination | 49 | 31_paragraph cohesion answer_paragraph cohesion_necessary sufficient paragraph cohesion_paragraph cohesion answer question |
|
73 |
+
| 32 | posted end semester lecture - class schedule - lectures posted - posted time coursework - posted end semester | 49 | 32_posted end semester lecture_class schedule_lectures posted_posted time coursework |
|
74 |
+
| 33 | meetings learnt great deal - meetings learnt great - online discussions fewer group - powerpoint slides group chat - online discussions fewer | 48 | 33_meetings learnt great deal_meetings learnt great_online discussions fewer group_powerpoint slides group chat |
|
75 |
+
| 34 | midterms classes - study midterm - final midterm exam - post mid term graded - midterm week final midterm | 48 | 34_midterms classes_study midterm_final midterm exam_post mid term graded |
|
76 |
+
| 35 | big box problem - midterm exam calculation questions - tables provide solutions idea - box problem - tables provide solutions | 48 | 35_big box problem_midterm exam calculation questions_tables provide solutions idea_box problem |
|
77 |
+
| 36 | probably respond email - provides cryptic terse responses - probably respond email said - knowing probably respond email - lack response sends email | 47 | 36_probably respond email_provides cryptic terse responses_probably respond email said_knowing probably respond email |
|
78 |
+
| 37 | points assignments lost - points exam example reason - points deducted stated powerpoint - points assignments lost points - points deducted quizzes | 47 | 37_points assignments lost_points exam example reason_points deducted stated powerpoint_points assignments lost points |
|
79 |
+
| 38 | felt experience achieved discouraging - honesty material interesting - honesty material interesting maybe - felt experience achieved - incredibly dull | 46 | 38_felt experience achieved discouraging_honesty material interesting_honesty material interesting maybe_felt experience achieved |
|
80 |
+
| 39 | promptly difficult time contacting - reread email - person email communications - reread email emailed meeting - reread email emailed | 46 | 39_promptly difficult time contacting_reread email_person email communications_reread email emailed meeting |
|
81 |
+
| 40 | plan outright fired incredibly - job exactly - nepotism influenced - outright fired incredibly - office hours solution shit | 46 | 40_plan outright fired incredibly_job exactly_nepotism influenced_outright fired incredibly |
|
82 |
+
| 41 | overwhelming student syllabus changed - questions midterm felt similarly - programming questions midterm felt - overwhelming student syllabus - repetitive semester things | 45 | 41_overwhelming student syllabus changed_questions midterm felt similarly_programming questions midterm felt_overwhelming student syllabus |
|
83 |
+
| 42 | feedback improve work - work feedback - improvement feedback - feedback improve - feedback provided | 44 | 42_feedback improve work_work feedback_improvement feedback_feedback improve |
|
84 |
+
| 43 | pages probably appropriate paper - page critique long think - think half page paragraph - paper assignment minimum pages - page critique long | 44 | 43_pages probably appropriate paper_page critique long think_think half page paragraph_paper assignment minimum pages |
|
85 |
+
| 44 | prompt feedback difficult - receive prompt feedback difficult - prompt feedback difficult evaluate - poor job communicating - receive prompt feedback | 44 | 44_prompt feedback difficult_receive prompt feedback difficult_prompt feedback difficult evaluate_poor job communicating |
|
86 |
+
| 45 | webex meetings - schools start webex meetings - webex meeting - record webex meetings - record webex meetings despite | 44 | 45_webex meetings_schools start webex meetings_webex meeting_record webex meetings |
|
87 |
+
| 46 | reply questions bit curt - request worth explaining - request worth explaining conveying - questions bit curt answers - posts felt interactive | 43 | 46_reply questions bit curt_request worth explaining_request worth explaining conveying_questions bit curt answers |
|
88 |
+
| 47 | mechanical engineering difficult institutions - understanding obstacles engineers face - engineering - engineering student - management program civil engineering | 43 | 47_mechanical engineering difficult institutions_understanding obstacles engineers face_engineering_engineering student |
|
89 |
+
| 48 | online proctoring - online proctoring services intrusive - online proctoring services - lockdown browser - old lockdown browser bit | 42 | 48_online proctoring_online proctoring services intrusive_online proctoring services_lockdown browser |
|
90 |
+
| 49 | reading discussed week assign - read book assignments posted - read book assignments - reading chapters assigned - question related reading week | 41 | 49_reading discussed week assign_read book assignments posted_read book assignments_reading chapters assigned |
|
91 |
+
| 50 | improvement responding emails work - response time emails - improvement responding emails - needs respond emails quicker - questions emails extremely | 40 | 50_improvement responding emails work_response time emails_improvement responding emails_needs respond emails quicker |
|
92 |
+
| 51 | problems demonstrate student learning - problems lectures example - problems lectures example homework - problems lectures - problems demonstrate student | 40 | 51_problems demonstrate student learning_problems lectures example_problems lectures example homework_problems lectures |
|
93 |
+
| 52 | response email emails - returned emails - reply email sent frustrating - response response week later - responded email assignment issues | 39 | 52_response email emails_returned emails_reply email sent frustrating_response response week later |
|
94 |
+
| 53 | learned julio accent hear - reminds teacher ferris beulers - possibly worst biggest loser - learned julio accent - julio accent hear | 39 | 53_learned julio accent hear_reminds teacher ferris beulers_possibly worst biggest loser_learned julio accent |
|
95 |
+
| 54 | recorded lectures need addressed - problematic audio lecture - outside noises recorded lectures - recording lectures poor - recording lectures poor potentially | 39 | 54_recorded lectures need addressed_problematic audio lecture_outside noises recorded lectures_recording lectures poor |
|
96 |
+
| 55 | material relevant examples conceptstheories - need basics extremely advanced - materials provided comprehensive understanding - work helpful sample - topics related | 37 | 55_material relevant examples conceptstheories_need basics extremely advanced_materials provided comprehensive understanding_work helpful sample |
|
97 |
+
| 56 | kind slow grader extremely - grader helpful lastly personality - helpful lastly personality favorable - kind knowledgeable communicative accommodating - helpful lastly personality | 36 | 56_kind slow grader extremely_grader helpful lastly personality_helpful lastly personality favorable_kind knowledgeable communicative accommodating |
|
98 |
+
| 57 | known personally nice guy - information forums great guy - great guy - intimidating super understanding knowledgeable - super understanding knowledgeable importantly | 34 | 57_known personally nice guy_information forums great guy_great guy_intimidating super understanding knowledgeable |
|
99 |
+
| 58 | mid final week notifications - deadlines - receive comments week dragging - result better discussions lateness - nonetheless discussion forums deadlines | 34 | 58_mid final week notifications_deadlines_receive comments week dragging_result better discussions lateness |
|
100 |
+
| 59 | read lengthy articles need - read lengthy articles - quality content understand subject - read write papers semester - read write papers | 33 | 59_read lengthy articles need_read lengthy articles_quality content understand subject_read write papers semester |
|
101 |
+
| 60 | loved taking khichis class - taking khichis class - person best professors pleasure - took class karnik available - took class karnik | 29 | 60_loved taking khichis class_taking khichis class_person best professors pleasure_took class karnik available |
|
102 |
+
| 61 | online section online sessions - purely online sections supposed - online sections supposed - online setting despite - purely online sections | 29 | 61_online section online sessions_purely online sections supposed_online sections supposed_online setting despite |
|
103 |
+
| 62 | professors willing communicate students - professors class year truly - professors willing communicate - professors far willing - let students experienced knowledgeable | 28 | 62_professors willing communicate students_professors class year truly_professors willing communicate_professors far willing |
|
104 |
+
| 63 | posts assignments fair weekly - repetitive syllabus weekly questions - posts assignments fair - questions posted students present - posts kinds assignments usual | 28 | 63_posts assignments fair weekly_repetitive syllabus weekly questions_posts assignments fair_questions posted students present |
|
105 |
+
| 64 | new year happy holidays - excellent dedication extremely thankful - happy new year - holidays happy new year - merry christmas happy | 28 | 64_new year happy holidays_excellent dedication extremely thankful_happy new year_holidays happy new year |
|
106 |
+
| 65 | knowing class need improve - worry stand class progress - teacher difficult determine learning - knowing class need - passing failing feel | 27 | 65_knowing class need improve_worry stand class progress_teacher difficult determine learning_knowing class need |
|
107 |
+
| 66 | questions posed students hour - reasonableenjoyable increased quiz time - questions minute test limit - questions week student reasonably - quizzes exams long capped | 27 | 66_questions posed students hour_reasonableenjoyable increased quiz time_questions minute test limit_questions week student reasonably |
|
108 |
+
| 67 | hard teach ethics - morality professionalism - hard teach ethics ethical - learn ethics - majoring professionalism synonymous ethics | 23 | 67_hard teach ethics_morality professionalism_hard teach ethics ethical_learn ethics |
|
109 |
+
| 68 | feedback add - add form add - form add - provide feedback add - add form add form | 21 | 68_feedback add_add form add_form add_provide feedback add |
|
110 |
+
| 69 | powerpoint came book youtube - powerpoints video - powerpoints making hypocritical - recorded lectures powerpoint - recorded lectures powerpoint minute | 16 | 69_powerpoint came book youtube_powerpoints video_powerpoints making hypocritical_recorded lectures powerpoint |
|
111 |
+
|
112 |
+
</details>
|
113 |
+
|
114 |
+
## Training hyperparameters
|
115 |
+
|
116 |
+
* calculate_probabilities: False
|
117 |
+
* language: None
|
118 |
+
* low_memory: False
|
119 |
+
* min_topic_size: 10
|
120 |
+
* n_gram_range: (1, 1)
|
121 |
+
* nr_topics: auto
|
122 |
+
* seed_topic_list: None
|
123 |
+
* top_n_words: 7
|
124 |
+
* verbose: True
|
125 |
+
* zeroshot_min_similarity: 0.7
|
126 |
+
* zeroshot_topic_list: None
|
127 |
+
|
128 |
+
## Framework versions
|
129 |
+
|
130 |
+
* Numpy: 1.26.4
|
131 |
+
* HDBSCAN: 0.8.39
|
132 |
+
* UMAP: 0.5.7
|
133 |
+
* Pandas: 2.2.3
|
134 |
+
* Scikit-Learn: 1.5.2
|
135 |
+
* Sentence-transformers: 3.2.1
|
136 |
+
* Transformers: 4.46.2
|
137 |
+
* Numba: 0.60.0
|
138 |
+
* Plotly: 5.24.1
|
139 |
+
* 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:fa6ebdb6284a1d6270f36978aa3028ed5160f8b3871c94a8c4684f404f31a346
|
3 |
+
size 4406124
|
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:e629149a01969dbf2ba723d6ad474c648281c06f460dca6f03b6c9d761ad33bf
|
3 |
+
size 215128
|
topics.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|