Understanding moral foundations can yield powerful results in terms of perceiving the intended meaning of the text data, as the concept of morality provides additional information on the unobservable characteristics of information processing and non-conscious cognitive processes. Considering that moral values vary significantly across cultures and yet many recurrent themes are observed and that each culture builds its societal and ideological narratives on top of its moral virtues, an enhanced understanding of morality can prove to be a valuable tool in deterring disinformation narratives by adversaries. Therefore, we investigate the evolution of latent moral loadings over time and across different sub-narratives on human and bot-generated tweets. For this purpose, we analyze the Syrian White Helmets-related tweets from April 1st, 2018 to April 30th, 2019. For the operationalization and quantification of moral rhetoric in tweets, we use Moral Foundations Dictionary in which five psychological dimensions (Harm/Care, Subversion/Authority, Cheating/Fairness, Betrayal/Loyalty and Degradation/Purity) are considered. Our results present the significant differences between the strength and patterns of moral rhetoric for human and bot-generated content on Twitter.
展开▼
