From hate to harmony: Leveraging large language models for safer speech in times of COVID-19 crisis.

This study investigates the rampant spread of offensive and derogatory language during the COVID-19 pandemic and aims to mitigate it through machine learning. Employing advanced Large Language Models (LLMs), the research develops a sophisticated framework adept at detecting and transforming abusive and hateful speech. The project begins by meticulously compiling a dataset, focusing specifically on Chinese language abuse and hate speech. It incorporates an extensive list of 30 pandemic-related terms, significantly enriching the resources available for this type of research. A two-tier detection model is then introduced, achieving a remarkable accuracy of 94.42 % in its first phase and an impressive 81.48 % in the second. Furthermore, the study enhances paraphrasing efficiency by integrating generative AI techniques, primarily Large Language Models, with a Latent Dirichlet Allocation (LDA) topic model. This combination allows for a thorough analysis of language before and after modification. The results highlight the transformative power of these methods. They show that the rephrased statements not only reduce the initial hostility but also preserve the essential themes and meanings. This breakthrough offers users effective rephrasing suggestions to prevent the spread of hate speech, contributing to more positive and constructive public discourse.

To Explore Intracerebral Hematoma with a Hybrid Approach and Combination of Discriminative Factors.

OBJECTIVES: To find discriminative combination of influential factors of Intracerebral hematoma (ICH) to cluster ICH patients with similar features to explore relationship among influential factors and 30-day mortality of ICH. METHODS: The data of ICH patients are collected. We use a decision tree to find discriminative combination of the influential factors. We cluster ICH patients with similar features using Fuzzy C-means algorithm (FCM) to construct a support vector machine (SVM) for each cluster to build a multi-SVM classifier. Finally, we designate each testing data into its appropriate cluster and apply the corresponding SVM classifier of the cluster to explore the relationship among impact factors and 30-day mortality. RESULTS: The two influential factors chosen to split the decision tree are Glasgow coma scale (GCS) score and Hematoma size. FCM algorithm finds three centroids, one for high danger group, one for middle danger group, and the other for low danger group. The proposed approach outperforms benchmark experiments without FCM algorithm to cluster training data. CONCLUSIONS: It is appropriate to construct a classifier for each cluster with similar features. The combination of factors with significant discrimination as input variables should outperform that with only single discriminative factor as input variable.

Effects of lactic acid bacteria isolated from fermented mustard on lowering cholesterol

Objective: To evaluate the ability of lactic acid bacteria (LAB) strains isolated from fermented mustard to lower the cholesterol in vitro.Methods:The ability of 50 LAB strains isolated from fermented mustard on lowering cholesterol in vitro was determined by modified o-phtshalaldehyde method. The LAB isolates were analyzed for their resistance to acid and bile salt. Strains with lowering cholesterol activity, were determined adherence to Caco-2 cells. Results: Strain B0007, B0006 and B0022 assimilated more cholesterol than BCRC10474 and BCRC 17010. The isolated strains showed tolerance to pH 3.0 for 3 h despite variations in the degree of viability and bile-tolerant strains, with more than 108 CFU/mL after incubation for 24 h at 1%oxigall in MRS. In addition, strain B0007 and B0022 identified as Lactobacillus plantarum with 16S rDNA sequences were able to adhere to the Caco-2 cell lines.Conclusions:These strains B0007 and B0022 may be potential functional sources for cholesterol-lowering activities as well as adhering to Caco-2 cell lines.