New method detects shared experiences in migration narratives using LLMs

Researchers have developed a new method to detect shared experiences in migration narratives, even when the language used is different. This technique, called experiential intertextuality detection, analyzes French narratives from migrants who traveled through the Trans-Saharan and Balkan routes. The study found that while simple text similarity methods have limited success, large language models like Qwen2.5-7B and Mistral-7B show promise, with Qwen2.5-7B achieving the best correlation with expert judgments. The research also highlighted that the position of a narrative within the migration journey significantly impacts the perceived experiential echoes. AI

IMPACT This research could lead to better tools for analyzing qualitative data in social sciences and humanities, particularly for understanding the experiences of vulnerable populations.

RANK_REASON The cluster contains an academic paper detailing a new method for text analysis. [lever_c_demoted from research: ic=1 ai=0.7]

Read on arXiv cs.CL →

• Arab slave trade
• Balkans
• French
• mistral:7b
• qwen2.5:7b
• Sakayo Toadoum Sari He

• paper
• other

AI-generated summary · Google Gemini · from 1 sources. How we write summaries →