Social Impact - Identifying Quotes of Literary Works in Social Networks
نویسندگان
چکیده
A non-neglectable amount of information shared in social networks has quotes to literary works that, most of the times, is not linked to the original work or author. Also, there are erroneous quotes that do not fully match the original work, for example by including synonyms and slang words. Moreover, users sometimes associate their quotes to the wrong author, which creates misleading information. This paper presents Social Impact framework as an approach to identify quotes in social networks and match them to the original literary works from a particular author. This framework was applied to two case-studies: O Mundo em Pessoa and Lusica. In the first case-study, Social Impact evaluation achieved 98% for precision measure and 59% for recall, whereas in the latter case-study it obtained 100% for precision and 53% of recall.
منابع مشابه
An Analysis of Social Systems in the Translation of The Great Gatsby
This article was written based on the key concept of polysystem theory which, in translating any literary text, emphasizes the transference of the social systems in which a text is embedded. As stated by Tynjanov (1978a), polysystem theory saw translated literature as a system operating in the larger social systems of the target text. Thus, the task of understanding as well as transferring such...
متن کاملA Critical Analysis of the Economic Discourse in Khaqani Shirvani’s Poems
Literary works are the carriers of many regulations, values, norms, beliefs, structures and existential, cultural, and social aspects of their time. Many of the social and cultural realities of past centuries embedded within the extant literary works of those centuries can be identified and followed through. The critical approach in discourse analysis of literary texts provides a more precise k...
متن کاملQuote Attribution for Literary Text with Neural Networks
We propose a method for using neural networks to attribute quotes in literary texts. Since previous work has been unable to successfully solve this problem based on bag-of-words features, we study the issue of whether this is due to the limited expressiveness of such features. By re-framing the modeling of quotes and characters as based off of word vectors, we hope to demonstrate that individua...
متن کاملIdentifying Speakers and Listeners of Quoted Speech in Literary Works
We present the first study that evaluates both speaker and listener identification for direct speech in literary texts. Our approach consists of two steps: identification of speakers and listeners near the quotes, and dialogue chain segmentation. Evaluation results show that this approach outperforms a rule-based approach that is stateof-the-art on a corpus of literary texts.
متن کاملExtracting Social Networks from Literary Fiction
We present a method for extracting social networks from literature, namely, nineteenth-century British novels and serials. We derive the networks from dialogue interactions, and thus our method depends on the ability to determine when two characters are in conversation. Our approach involves character name chunking, quoted speech attribution and conversation detection given the set of quotes. W...
متن کامل