Curbing hate speech is undoubtedly a major challenge for online microblogging platforms like Twitter. While there have been studies around hate speech detection, it is not clear how hate speech finds its way into an online discussion. It is important for a content moderator to not only identify which tweet is hateful, but also to predict which tweet will be responsible for accumulating hate speech. This would help in prioritizing tweets that need constant monitoring. Our analysis reveals that for hate speech to manifest in an ongoing discussion, the source tweet may not necessarily be hateful; rather, there are plenty of such non-hateful tweets which gradually invoke hateful replies, resulting in the entire reply threads becoming provocative.In this paper, we define a novel problemgiven a source tweet and a few of its initial replies, the task is to forecast the hate intensity of upcoming replies. To this end, we curate a novel dataset constituting ∼ 4.5 contemporary tweets and their entire reply threads. Our preliminary analysis confirms that the evolution patterns along time of hate intensity among reply threads have highly diverse patterns, and there is no significant correlation between the hate intensity of the source tweets and that of their reply threads. We employ seven state-of-the-art dynamic models (either statistical signal processing or deep learning based) and show that they fail badly to forecast the hate intensity. We then propose DESSERT, a novel deep state-space model that leverages the function approximation capability of deep neural networks with the capacity to quantify the uncertainty of statistical signal processing models. Exhaustive experiments and ablation study show that DESSERT outperforms all the baselines substantially. Further, its deployment in an advanced AI platform designed to monitor real-world problematic hateful content has improved the aggregated insights extracted for countering the spread of online harms.T. Chakraborty would like to acknowledge the support of Logically, the Ramanujan Fellowship, and the Infosys Centre for AI, IIIT Delhi. We also thank Sarah Masud for her help in writing the paper. CCS CONCEPTS• Computing methodologies → Machine learning algorithms;• Information systems → Social tagging systems; • Humancentered computing → Social network analysis.

No abstract

No abstract

The present study enumerates the attenuating effects of curcumin and α-tocopherol against propoxur induced oxidative DNA damage in human peripheral blood mononuclear cells (PBMC). Cultured cells were isolated from peripheral blood of healthy volunteers, and were exposed to varying concentrations of propoxur (0-21 μg/ml) for 6, 12, and 24 h, and in combination with curcumin (9.2 μg/ml) or α-tocopherol (4.3 μg/ml) or both. Cytotoxic effect of propoxur was examined by MTT assay. The role of oxidative stress beneath the cytotoxicity of propoxur was evaluated by the measurement of reduced glutathione (GSH), malondialdehyde (MDA) and 8-hydroxy-2'-deoxyguanosine (8-OH-dG) levels in cell lysate. A concentration-dependent cell death, depletion of GSH, an increase in the level of both MDA and 8-OH-dG were observed. Co-treatment with curcumin or α-tocopherol significantly attenuates depleted GSH, decrease in MDA and 8-OH-dG levels in propoxur exposed cells (p < 0.05). The results of the present study provide experimental evidence of involvement of oxidative stress in propoxur-mediated genotoxicity in human PBMC and highlight the antioxidant role of curcumin and α-tocopherol following propoxur exposure.