Social media sites such as YouTube and Facebook have become an integral part of everyone's life and in the last few years, hate speech in the social media comment section has increased rapidly. Detection of hate speech on social media websites faces a variety of challenges including small imbalanced data sets, the finding of an appropriate model and also the choice of feature analysis method. Furthermore, this problem is more severe for the Bengali speaking community due to the lack of gold standard labelled datasets. This paper presents a new dataset of 30,000 user comments tagged by crowdsourcing and verified by expert. All the user comments collected from YouTube and Facebook comment section and to classified into seven categories: sports, entertainment, religion, politics, crime, celebrity, and TikTok & meme. A total of 50 annotators annotated each comment three times, and the majority vote was taken as the final annotation. Nevertheless, we have conducted baseline experiments and several deep learning models along with extensive pretrained Bengali word embedding such as Word2Vec, FastTest, and BengFastText on this dataset to facilitate future research opportunities. The experiment illustrated that although all the deep learning model performed well, SVM achieved the best result with 87.5% accuracy. Our core contribution is to make this benchmark dataset available and accessible to facilitate further research in the field of Bengali hate speech detection.
In this paper, two different models of highly nonlinear bored core photonic crystal fibers (HNL-BCPCF) are presented and compared for attaining an ultra-high negative dispersion coefficient and high nonlinearity. We achieved this dispersion by tailoring a defect into the solid core of the two proposed models and appropriately scaling down the diameter of the neighboring airholes of the core. To investigate the optical transmission properties in the fiber, simulations were carried out employing the finite element method (FEM) having a perfectly matched layer. The simulation results exhibited large negative dispersion coefficients of − 2218 ps/(nm-km) and − 2221 ps/(nm-km) for the two proposed models, respectively, when the wavelength had been tuned to 1550 nm and the corresponding nonlinear coefficients stand out to be 117.6 W −1 km −1 and 118.4 W −1 km −1. The fabrication process had been made much more feasible as the design consists of circular airholes. In our analysis, this geometry of photonic crystal fiber is noticeably more robust for its successful achievement of an ultra-high negative dispersion with high nonlinearity and facilitates optical back propagation applications and dispersion compensation for optical transmission systems.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.