Search for: All records

The political stance prediction for news articles has been widely studied to mitigate the echo chamber effect – people fall into their thoughts and reinforce their pre-existing beliefs. The previous works for the political stance problem focus on (1) identifying political factors that could reflect the political stance of a news article and (2) capturing those factors effectively. Despite their empirical successes, they are not sufficiently justified in terms of how effective their identified factors are in the political stance prediction. Motivated by this, in this work, we conduct a user study to investigate important factors in political stance prediction, and observe that the context and tone of a news article (implicit) and external knowledge for real-world entities appearing in the article (explicit) are important in determining its political stance. Based on this observation, we propose a novel knowledge-aware approach to political stance prediction (KHAN), employing (1) hierarchical attention networks (HAN) to learn the relationships among words and sentences in three different levels and (2) knowledge encoding (KE) to incorporate external knowledge for real-world entities into the process of political stance prediction. Also, to take into account the subtle and important difference between opposite political stances, we build two independent political knowledge graphs (KG) (i.e., KG-lib and KG-con) by ourselves and learn to fuse the different political knowledge. Through extensive evaluations on three real-world datasets, we demonstrate the superiority of KHAN in terms of (1) accuracy, (2) efficiency, and (3) effectiveness. 

Abstract Light initiates chloroplast biogenesis inArabidopsisby eliminating PHYTOCHROME-INTERACTING transcription FACTORs (PIFs), which in turn de-represses nuclear photosynthesis genes, and synchronously, generates a nucleus-to-plastid (anterograde) signal that activates the plastid-encoded bacterial-type RNA polymerase (PEP) to transcribe plastid photosynthesis genes. However, the identity of the anterograde signal remains frustratingly elusive. The main challenge has been the difficulty to distinguish regulators from the plethora of necessary components for plastid transcription and other essential chloroplast functions, such as photosynthesis. Here, we show that the genome-wide induction of nuclear photosynthesis genes is insufficient to activate the PEP. PEP inhibition is imposed redundantly by multiple PIFs and requires PIF3’s activator activity. Among the nuclear-encoded components of the PEP holoenzyme, we identify four light-inducible, PIF-repressed sigma factors as anterograde signals. Together, our results elucidate that light-dependent inhibition of PIFs activates plastid photosynthesis genes via sigma factors as anterograde signals in parallel with the induction of nuclear photosynthesis genes.