manuto59 commited on
Commit
fe3e975
1 Parent(s): 4d094d5

add model card

Browse files
Files changed (1) hide show
  1. README.md +27 -0
README.md ADDED
@@ -0,0 +1,27 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ language: en # <-- my language
3
+ widget:
4
+ - text: "Still unemployed..."
5
+ ---
6
+
7
+ # Detection of employment status disclosures on Twitter
8
+
9
+ ## Model main characteristics:
10
+ - class: Is Unemployed(1), else (0)
11
+ - country: US
12
+ - language: English
13
+ - architecture: BERT base
14
+
15
+ ## Model description
16
+ This model is a version of `DeepPavlov/bert-base-cased-conversational` finetuned to recognize English tweets where a user mentions that she is unemployed. It was trained on English tweets from US-based users. The task is framed as binary classification problem with:
17
+ - the positive class referring to tweets mentioning that a user was recently hired (label=1)
18
+ - the negative class referring to all other tweets (label=0)
19
+
20
+ ## Resources
21
+
22
+ The dataset of English tweets on which this classifier was trained is open-sourced [here](https://github.com/manueltonneau/twitter-unemployment).
23
+ Details on the performance can be found in our [ACL 2022 paper](https://arxiv.org/abs/2203.09178).
24
+
25
+ ## Citation
26
+
27
+ If you find this model useful, please cite our paper (citation to come soon).