| import os | |
| import torch | |
| import dash | |
| import streamlit as st | |
| import pandas as pd | |
| import json | |
| import random | |
| import firebase_admin | |
| from transformers import AutoTokenizer, AutoModelForSequenceClassification | |
| from transformers import pipeline | |
| from firebase_admin import credentials, firestore | |
| from dotenv import load_dotenv | |
| import plotly.graph_objects as go | |
| import demo_section | |
| import explore_data_section | |
| load_dotenv() | |
| if 'collect_data' not in st.session_state: | |
| st.session_state.collect_data = True | |
| if 'user_id' not in st.session_state: | |
| st.session_state.user_id = random.randint(1, 9999999) | |
| st.markdown(""" | |
| # Machine-Based Item Desirability Ratings | |
| This web application accompanies the paper "*Expanding the Methodological Toolbox: Machine-Based Item Desirability Ratings as an Alternative to Human-Based Ratings*". | |
| *Hommel, B. E. (2023). Expanding the methodological toolbox: Machine-based item desirability ratings as an alternative to human-based ratings. Personality and Individual Differences, 213, 112307. https://doi.org/10.1016/j.paid.2023.112307* | |
| ## What is this research about? | |
| Researchers use personality scales to measure people's traits and behaviors, but biases can affect the accuracy of these scales. | |
| Socially desirable responding is a common bias that can skew results. To overcome this, researchers gather item desirability ratings, e.g., to ensure that questions are neutral. | |
| Recently, advancements in natural language processing have made it possible to use machines to estimate social desirability ratings, | |
| which can provide a viable alternative to human ratings and help researchers, scale developers, and practitioners improve the accuracy of personality scales. | |
| """) | |
| demo_section.show() | |
| explore_data_section.show() |