|
Activity Number:
|
433
- Statistical Approaches in Text Analysis
|
|
Type:
|
Topic-Contributed
|
|
Date/Time:
|
Thursday, August 12, 2021 : 4:00 PM to 5:50 PM
|
|
Sponsor:
|
Text Analysis Interest Group
|
|
Abstract #317445
|
|
|
Title:
|
On the Need for More Statistics in Text Analysis, with Recent Advances
|
|
Author(s):
|
Jordan Rodu* and Michael Baiocchi
|
|
Companies:
|
University of Virginia and Stanford University
|
|
Keywords:
|
text analysis;
NLP
|
|
Abstract:
|
We argue for the need for more statistical thinking in text analysis. Recent advances in computer science have dominated the text analysis landscape (often called natural language processing (NLP)). But these exciting developments have left large gaps in their wake, particularly in places where our scientific colleagues most need robust approaches. We provide a theoretical justification for why NLP techniques are often not suitable, and encourage statisticians to work on principled methodologies to provide alternatives. Some current advances are highlighted.
|
Authors who are presenting talks have a * after their name.
