As online social media evolve with the advance of the Internet in our daily life, people write about many things, targeting different audiences. Perhaps, “talking” would be a better expression than “writing” in this context due to a deluge of political commentaries and conversations, particularly on social media.
Many social and computer scientists have studied to understand what kinds of patterns we can identify and proposed ways of how computers automatically classify different semantic meanings or sentiment of texts on online social platforms. Although the feasibility of the task is still arguable, there has been some improvement in the quality of prediction.
For computer-based predictions or recommendations, machine learning approach takes the core responsibility since its role is the judgment based on a priori knowledge. This knowledge is usually in the form of systemic rule or consistent pattern. For example, computer tokenizes each sentence into individual elements (words) and deduce a possible context among a few candidates based on grammatical rules. Part of speech (word class or lexical class) tagging is one of the well-established rules in natural language processing.
However, in the context of political sarcasm or satire, which is one of the most common practices in social media, it would be impossible to rely solely on these grammatical rules. Most of the expressions in the context do not mean as it is said. The irony in writing has been studied for a long time, yet this is still considered as an unreliable feature among computer scientists. I think the key obstacle in this study is the unpatterned discrepancy between the superficial meaning of the text and the real semantic underneath the appearance.
Cultural dependency as a nature of written sarcasm is another big challenge. This dependency makes the task a multi-dimensional problem that involves many dependent variables. Besides the variables are mostly topic-specific, context-dependent and temporal.