PulseAugur
LIVE 06:23:53
research · [2 sources] ·
0
research

New semisupervised technique uses masked language models for polarity analysis

Researchers have developed a novel semisupervised technique for polarity analysis that leverages masked language models, specifically word2vec. This new approach, a variation of Latent Semantic Scaling (LSS), assigns polarity scores as predicted probabilities, offering greater accuracy and interpretability compared to traditional spatial models. The method was tested on China Daily's reporting during the COVID-19 pandemic, demonstrating its effectiveness in analyzing sentiment in text. AI

Summary written by gemini-2.5-flash-lite from 2 sources. How we write summaries →

IMPACT Introduces a more accurate and interpretable method for sentiment analysis using advanced language models.

RANK_REASON Academic paper detailing a new technique for polarity analysis using masked language models.

Read on arXiv cs.CL →

COVERAGE [2]

  1. arXiv cs.CL TIER_1 · Kohei Watanabe ·

    A New Semisupervised Technique for Polarity Analysis using Masked Language Models

    arXiv:2604.26230v1 Announce Type: new Abstract: I developed a new version of Latent Semantic Scaling (LSS) employing word2vec as a masked language model. Unlike original spatial models, it assigns polarity scores to words and documents as predicted probabilities of seed words to …

  2. arXiv cs.CL TIER_1 · Kohei Watanabe ·

    A New Semisupervised Technique for Polarity Analysis using Masked Language Models

    I developed a new version of Latent Semantic Scaling (LSS) employing word2vec as a masked language model. Unlike original spatial models, it assigns polarity scores to words and documents as predicted probabilities of seed words to occur in given contexts. These probabilistic pol…