In the wake of a polarizing election, the cyber world is laden with hate speech. Context accompanying a hate speech text is useful for identifying hate speech, which however has been largely overlooked in existing datasets and hate speech detection models. In this paper, we provide an annotated corpus of hate speech with context information well kept. Then we propose two types of hate speech detection models that incorporate context information, a logistic regression model with context features and a neural network model with learning components for context. Our evaluation shows that both models outperform a strong baseline by around 3% to 4% in F1 score and combining these two models further improve the performance by another 7% in F1 score.
The public-private-partnership (PPP) is a new mode for the government and social capital to jointly invest in public infrastructure projects. In particular, PPP projects for new energy power construction have been strongly supported in some countries in recent years, because it can not only reduce financial pressure on the government, but also promote the development of new energy. Current scholars study the economic benefits of PPP projects for new energy power construction from a macro perspective, and they rarely study behavioral strategies of the government and social capital as a game process of project construction from a micro perspective. This paper will fill this gap. This study firstly built an evolutionary game model of the government and investors based on new energy power construction PPP projects. Secondly, taking China’s typical new energy power construction PPP project–waste incineration power generation as an example, the system dynamics (SD) model was proposed to simulate the evolutionary process of game players’ behavioral strategies. Finally, the effects of key factors in the construction of PPP project on the strategies’ stability were studied. The results show that: (1) there is no evolutionarily stable strategy (ESS) in the game system between the government and investors, and system evolution is characterized by periodic behavior. (2) When the government implements dynamic bounty measures, the system evolution process is still a closed loop with periodic motion. However, when the government implements dynamic punishment measures, there is a stable ESS in the hybrid strategy of the game system. (3) The government can increase unit fines when making dynamic strategic adjustments, which will not only promote the active cooperation of investors, but also reduce the probability of government supervision, thereby reducing costs.
We aim to comprehensively identify all the event causal relations in a document, both within a sentence and across sentences, which is important for reconstructing pivotal event structures. The challenges we identified are two: 1) event causal relations are sparse among all possible event pairs in a document, in addition, 2) few causal relations are explicitly stated. Both challenges are especially true for identifying causal relations between events across sentences. To address these challenges, we model rich aspects of document-level causal structures for achieving comprehensive causal relation identification. The causal structures include heavy involvements of document-level main events in causal relations as well as several types of finegrained constraints that capture implications from certain sentential syntactic relations and discourse relations as well as interactions between event causal relations and event coreference relations. Our experimental results show that modeling the global and fine-grained aspects of causal structures using Integer Linear Programming (ILP) greatly improves the performance of causal relation identification, especially in identifying cross-sentence causal relations.
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.