Phillip Schmedeman
Biographic Data
| ID | 6880352 |
|---|---|
| NAME | Phillip Schmedeman |
| GIVEN NAMES | Phillip |
| FAMILY NAME | Schmedeman |
| SIGNATURE | SCHMEDEMAN P |
| AFFILIATIONS | United States Military Academy |
| ORCID | 0000-0002-2463-3879 |
| VERIFIED | Yes |
| TOTAL WORKS | 1 |
| TOTAL CITATIONS | 6 |
| WORKS AS AUTHOR | 1 |
| WORKS AS EDITOR | 0 |
| FIRST PUBLICATION YEAR | 2024 |
| LATEST PUBLICATION YEAR | 2024 |
| H-INDEX | 1 |
Do AIs know what the most important issue is? Using language models to code open-text social survey responses at scale
Can artificial intelligence accurately label open-text survey responses? We compare the accuracy of six large language models (LLMs) using a few-shot approach, three supervised learning algorithms (SVM, DistilRoBERTa, and a neural network trained on BERT embeddings), and a second human coder on the task of categorizing “most important issue” responses from the British Election Study Internet Panel into 50 categories. For the scenario where a rese…
Do AIs know what the most important issue is? Using language models to code open-text social survey responses at scale
Can artificial intelligence accurately label open-text survey responses? We compare the accuracy of six large language models (LLMs) using a few-shot approach, three supervised learning algorithms (SVM, DistilRoBERTa, and a neural network trained on BERT embeddings), and a second human coder on the task of categorizing “most important issue” responses from the British Election Study Internet Panel into 50 categories. For the scenario where a rese…
Do AIs know what the most important issue is? Using language models to code open-text social survey responses at scale
Can artificial intelligence accurately label open-text survey responses? We compare the accuracy of six large language models (LLMs) using a few-shot approach, three supervised learning algorithms (SVM, DistilRoBERTa, and a neural network trained on BERT embeddings), and a second human coder on the task of categorizing “most important issue” responses from the British Election Study Internet Panel into 50 categories. For the scenario where a rese…
Artificial Intelligence (1 work) · Artificial neural network (1 work) · Code (set theory (1 work) · Computational and Text Analysis Methods (1 work) · Computer Science (1 work) · Electoral Systems and Political Participation (1 work) · Engineering (1 work) · Geography (1 work) · Language model (1 work) · Machine learning (1 work)