Machine learning models detect user deaths on social media

A new dissertation details the development of machine learning classifiers capable of automatically detecting deceased users on social networking sites. The research utilized a new dataset compiled from Wikidata and X (formerly Twitter), training various models including traditional algorithms like SVM and RF, as well as deep learning models such as BiLSTM, CNN, and BERT. The study found that BERT achieved the highest performance, outperforming all other models. Analysis of linguistic characteristics revealed that post-mortem tweets exhibit higher negative sentiment and more frequent use of words related to negativity, family, religion, and death, while pre-mortem tweets show higher neutral sentiment and more frequent use of impersonal pronouns and informal language. AI

IMPACT This research could lead to more sensitive and automated methods for managing digital legacies and understanding online social dynamics.

RANK_REASON Academic paper detailing novel ML models and dataset for a specific task. [lever_c_demoted from research: ic=1 ai=1.0]

Read on arXiv cs.AI →

• Bert
• BiLSTM
• CNN
• fastText
• glove
• k-nearest neighbors algorithm
• support vector machine
• tf–idf
• Wikidata
• Word2vec
• X

• paper
• other

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