The field of natural language processing (NLP) is witnessing significant advancements in its applications to healthcare and social issues. Researchers are exploring innovative methods to identify and address underreporting of notifiable events, such as gender-based violence, in healthcare settings. The use of semantic frames and machine learning models is becoming increasingly popular in this domain. Furthermore, there is a growing interest in developing NLP tools for low-resource languages to detect and mitigate sexism and other forms of social exclusion. The development of multilingual benchmarks and evaluation frameworks is also gaining traction, with a focus on assessing the robustness of large language models in capturing cultural nuances and presuppositions. Noteworthy papers in this area include:

• A study that introduces a methodology for identifying underreporting of gender-based violence in e-medical records using semantic frames, achieving a precision of 0.726.
• A paper that presents the first Hausa sexism detection dataset and experiments with machine learning classifiers and pre-trained multilingual language models to detect sexism in low-resource languages.