Spaces:
Sleeping
Sleeping
add ABOUT.md file
Browse files
ABOUT.md
ADDED
@@ -0,0 +1,18 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
# ROTA
|
2 |
+
## Rapid Offense Text Autocoder
|
3 |
+
|
4 |
+
### ℹ️ Intro
|
5 |
+
|
6 |
+
[![HuggingFace Models](https://img.shields.io/badge/%F0%9F%A4%97%20models-2021.05.18.15-blue)](https://huggingface.co/rti-international/rota)
|
7 |
+
[![GitHub Model Release](https://img.shields.io/github/v/release/RTIInternational/rota?logo=github)](https://github.com/RTIInternational/rota)
|
8 |
+
[![DOI](https://zenodo.org/badge/DOI/10.5281/zenodo.4770492.svg)](https://doi.org/10.5281/zenodo.4770492)
|
9 |
+
|
10 |
+
Criminal justice research often requires conversion of free-text offense descriptions into overall charge categories to aid analysis. For example, the free-text offense of "eluding a police vehicle" would be coded to a charge category of "Obstruction - Law Enforcement". Since free-text offense descriptions aren't standardized and often need to be categorized in large volumes, this can result in a manual and time intensive process for researchers. ROTA is a machine learning model for converting offense text into offense codes.
|
11 |
+
|
12 |
+
Currently ROTA predicts the *Charge Category* of a given offense text. A *charge category* is one of the headings for offense codes in the [2009 NCRP Codebook: Appendix F](https://www.icpsr.umich.edu/web/NACJD/studies/30799/datadocumentation#).
|
13 |
+
|
14 |
+
The model was trained on [publicly available data](https://web.archive.org/web/20201021001250/https://www.icpsr.umich.edu/web/pages/NACJD/guides/ncrp.html) from a crosswalk containing offenses from all 50 states combined with three additional hand-labeled offense text datasets.
|
15 |
+
|
16 |
+
For more information on the model, please see the [model repo](https://huggingface.co/rti-international/rota).
|
17 |
+
|
18 |
+
This model and application were developed by the [RTI International Center for Data Science](https://www.rti.org/centers/rti-center-data-science).
|
README.md
CHANGED
@@ -1,8 +1,8 @@
|
|
1 |
---
|
2 |
-
title: ROTA App
|
3 |
-
emoji:
|
4 |
-
colorFrom:
|
5 |
-
colorTo:
|
6 |
sdk: streamlit
|
7 |
sdk_version: 1.15.2
|
8 |
app_file: app.py
|
|
|
1 |
---
|
2 |
+
title: ROTA App: Rapid Offense Text Autocoder
|
3 |
+
emoji: ⚡️
|
4 |
+
colorFrom: blue
|
5 |
+
colorTo: white
|
6 |
sdk: streamlit
|
7 |
sdk_version: 1.15.2
|
8 |
app_file: app.py
|
app.py
CHANGED
@@ -14,7 +14,7 @@ PRED_BATCH_SIZE = 4
|
|
14 |
|
15 |
st.set_page_config(page_title="ROTA", initial_sidebar_state="collapsed")
|
16 |
|
17 |
-
st.markdown(Path("
|
18 |
|
19 |
st.markdown("## ✏️ Single Coder Demo")
|
20 |
input_text = st.text_input(
|
|
|
14 |
|
15 |
st.set_page_config(page_title="ROTA", initial_sidebar_state="collapsed")
|
16 |
|
17 |
+
st.markdown(Path("ABOUT.md").read_text())
|
18 |
|
19 |
st.markdown("## ✏️ Single Coder Demo")
|
20 |
input_text = st.text_input(
|