Social media platforms have a vital role in the modern world, serving as conduits for communication, the exchange of ideas, and the establishment of networks. However, the misuse of these platforms through toxic comments, which can range from offensive remarks to hate speech, is a concerning issue. This study focuses on identifying toxic comments in the Bengali language targeting three specific groups: transgender people, indigenous people, and migrant people, from multiple social media sources. The study delves into the intricate process of identifying and categorizing toxic language while considering the varying degrees of toxicity: high, medium, and low. The methodology involves creating a dataset, manual annotation, and employing pre-trained transformer models like Bangla-BERT, bangla-bert-base, distil-BERT, and Bert-base-multilingual-cased for classification. Diverse assessment metrics such as accuracy, recall, precision, and F1-score are employed to evaluate the model's effectiveness. The experimental findings reveal that Bangla-BERT surpasses alternative models, achieving an F1-score of 0.8903. This research exposes the complexity of toxicity in Bangla social media dialogues, revealing its differing impacts on diverse demographic groups.

Standard approaches to hate speech detection rely on sufficient available hate speech annotations. Extending previous work that repurposes natural language inference (NLI) models for zero-shot text classification, we propose a simple approach that combines multiple hypotheses to improve English NLI-based zero-shot hate speech detection. We first conduct an error analysis for vanilla NLI-based zero-shot hate speech detection and then develop four strategies based on this analysis. The strategies use multiple hypotheses to predict various aspects of an input text and combine these predictions into a final verdict. We find that the zero-shot baseline used for the initial error analysis already outperforms commercial systems and fine-tuned BERT-based hate speech detection models on HateCheck. The combination of the proposed strategies further increases the zero-shot accuracy of 79.4% on HateCheck by 7.9 percentage points (pp), and the accuracy of 69.6% on ETHOS by 10.0pp.

Transgender community is experiencing a huge disparity in mental health conditions compared with the general population. Interpreting the social medial data posted by transgender people may help us understand the sentiments of these sexual minority groups better and apply early interventions. In this study, we manually categorize 300 social media comments posted by transgender people to the sentiment of negative, positive, and neutral. 5 machine learning algorithms and 2 deep neural networks are adopted to build sentiment analysis classifiers based on the annotated data. Results show that our annotations are reliable with a high Cohen's Kappa score over 0.8 across all three classes. LSTM model yields an optimal performance of accuracy over 0.85 and AUC of 0.876. Our next step will focus on using advanced natural language processing algorithms on a larger annotated dataset.

Although there are millions of transgender people in the world, a lack of information exists about their health issues. This issue has consequences for the medical field, which only has a nascent understanding of how to identify and meet this population's health-related needs. Social media sites like Twitter provide new opportunities for transgender people to overcome these barriers by sharing their personal health experiences. Our research employs a computational framework to collect tweets from self-identified transgender users, detect those that are health-related, and identify their information needs. This framework is significant because it provides a macro-scale perspective on an issue that lacks investigation at national or demographic levels. Our findings identified 54 distinct health-related topics that we grouped into 7 broader categories. Further, we found both linguistic and topical differences in the health-related information shared by transgender men (TM) as com-pared to transgender women (TW). These findings can help inform medical and policy-based strategies for health interventions within transgender communities. Also, our proposed approach can inform the development of computational strategies to identify the health-related information needs of other marginalized populations.

The following essay is reprinted with permission from The Conversation, an online publication covering the latest research. Imagine walking down the street and seeing advertising screens change their content based on how you walk, how you talk, or even the shape of your chest. These screens rely on hidden cameras, microphones and computers to guess if you're male or female. This might sound futuristic, but patrons in a Norwegian pizzeria discovered it's exactly what was happening: Women were seeing ads for salad and men were seeing ads for meat options. The software running a digital advertising board spilled the beans when it crashed and displayed its underlying code.

Since the popular dating app Tinder launched in 2012, new users have been given two options to describe themselves when they sign up: male or female. But that seemingly simple question presented a conundrum for people like Liz Busillo, a graphic designer in Philadelphia who identifies as agender--meaning Busillo identifies as neither a man, nor a woman. "I figured, I present in a way that's very feminine, so I'll just put down female and clarify in my profile," says Busillo, who uses the singular pronoun they. What ensued was a slew of negative interactions, mostly with straight men, including aggression, harassment, and someone reporting their profile for being "fake." Many other transgender and gender non-conforming Tinder users have reported similar experiences on a platform where gender was presumed to be as straightforward as swiping left or right.

Cannes Lions this year saw the ad industry expanding its creative capabilities. Over 13,500 delegates from about 90 countries descended on Cannes again this year hoping for a Lion in one of 17 categories. With awards honoring work from design to creative data to radio, the ceremonies reflected a complex industry drawing on a broader range of creative disciplines than in the past, but also facing unprecedented challenges in making campaigns work across channels. "There's never been so many channels or points of interactions, or agencies working on various parts of that," said Keith Weed, chief marketing and communications officer at Unilever. "It's important to make sure the brand experience does not get fragmented."