Research map / Label-efficient and robust learning / Recognition and long-tail
GlobalTrait: Personality Alignment of Multilingual Word Embeddings
Farhad Bin Siddique, Dario Bertero, Pascale Fung
Read the paperCheck your idea against 137,217 papers
AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.
Measured effects reported in the paper
| What was changed | Where | Measured | Effect |
|---|---|---|---|
| Use multilingual training with GlobalTrait-aligned embeddings in a two-channel CNN instead of monolingual CNN embeddings | CNN personality classifier · PAN 2015 Spanish | F-score (average): 71.1 -> 74.6 | Improved |
| Use multilingual training with GlobalTrait-aligned embeddings in a two-channel CNN instead of monolingual CNN embeddings | CNN personality classifier · PAN 2015 Italian | F-score (average): 68.1 -> 68.2 | Improved |
| Use multilingual training with GlobalTrait-aligned embeddings in a two-channel CNN instead of monolingual CNN embeddings | CNN personality classifier · PAN 2015 Dutch | F-score (average): 68.4 -> 77.5 | Improved |
| Use multilingual training with GlobalTrait-aligned embeddings instead of monolingual embeddings | CNN personality classifier · Chinese personality corpus | F-score (average): 58.8 -> 62.3 | Improved |
| Use GlobalTrait-aligned embeddings in CNN regression instead of tf-idf linear regression | Personality regression · PAN 2015 Spanish | RMSE (average): 0.147 -> 0.149 | Hurt |
| Use GlobalTrait-aligned embeddings in CNN regression instead of tf-idf linear regression | Personality regression · PAN 2015 Italian | RMSE (average): 0.124 -> 0.127 | Hurt |
| Use GlobalTrait-aligned multilingual embeddings rather than monolingual embeddings | Logistic regression personality classifier · PAN 2015 Spanish | F-score (average): 68.2 -> 72.2 | Improved |
| Use GlobalTrait-aligned multilingual embeddings rather than monolingual embeddings | Logistic regression personality classifier · PAN 2015 Italian | F-score (average): 58.0 -> 64.1 | Improved |
| Use GlobalTrait-aligned multilingual embeddings rather than monolingual embeddings | Logistic regression personality classifier · PAN 2015 Dutch | F-score (average): 68.8 -> 65.3 | Hurt |
| Use multilingual training with GlobalTrait-aligned embeddings in a two-channel CNN instead of monolingual CNN embeddings | CNN personality classifier · PAN 2015 Spanish, Italian, and Dutch | F-score (average): 71.1 -> 74.6; 68.1 -> 68.2; 68.4 -> 77.5 | Mixed |
| Add English training data and GlobalTrait alignment for Chinese | Multilingual personality classifier · Chinese personality corpus | F-score (average): 57.6 -> 61.9; 58.8 -> 62.3 | Improved |
Closest papers by meaning
- Personality Alignment of Large Language Models (ICLR 2025 · similarity 0.87)
- PICLe: Eliciting Diverse Behaviors from Large Language Models with Persona In-Context Learning (ICML 2024 · similarity 0.85)
- MMTEB: Massive Multilingual Text Embedding Benchmark (ICLR 2025 · similarity 0.85)
- LLM vs Small Model? Large Language Model Based Text Augmentation Enhanced Personality Detection Model (AAAI 2024 · similarity 0.85)
- Neuron based Personality Trait Induction in Large Language Models (ICLR 2025 · similarity 0.84)
- The Language Model Can Have the Personality: Joint Learning for Personality Enhanced Language Model (Student Abstract) (AAAI 2024 · similarity 0.84)
Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.
