九州大学 · 社会科学
ピユーシュ・ガシヤ教授の研究室は、SNSや新聞メディアを対象とした自然言語処理(NLP)とネットワーク分析を用いて、グローバルな社会的・政治的出来事における言語的・感情的傾向を解明する研究を行っています。特に、パンデミック時における報道の傾向、宗教的・民族的差別、戦争報道、国際関係におけるメディアの役割など、社会的緊張や危機状況における情報発信の仕組みに注目しています。近年では、Twitter や Telegram などのプラットフォームを活用した大規模なテキスト分析を通じて、極右思想やイスラム嫌悪、国家的イデオロギーの言説的展開を定量的に分析する取り組みも展開しています。
Figures are computed from collected data and may differ slightly.
Newspapers are very important for a society as they inform citizens about the events around them and how they can impact their life. Their importance becomes more crucial and indispensable in the times of health crisis such as the current COVID-19 pandemic. Since the starting of this pandemic newspapers are providing rich information to the public about various issues such as the discovery of a new strain of coronavirus, lockdown and other restrictions, government policies, and information relat
The COVID-19 pandemic brought about several challenges in addition to the virus itself. The rise of Islamophobic hate speech on social media is one such challenge. As countries were coping with economic collapse due to mass lockdown, hateful people, especially those associated with far-right groups, were targeting and blaming Muslims for the spread of the coronavirus. In India, where intense religious/communal polarization is taking place under the right-wing Bharatiya Janata Party (BJP)-led gov
The popularity of the instant messaging app Telegram in Ukraine and Russia was already high before the still-ongoing Russian invasion of Ukraine. However, since 24 February 2022 (when the Russian invasion began), it has seen huge increases in subscribers and has even become the primary communication and news source in Ukraine. In this exploratory research, we analyzed Telegram channels from both Ukraine (@UkraineNow — the official channel of the Ukrainian government, and @V_Zelenskiy_official —
Abstract For Japan—a country that has always been described with virtually no major natural resources such as oil, gas, and coal—the Middle Eastern region has a special place in its economic and foreign policy. In 2017, 39% of Japan’s energy came from oil, and 87% of Japan’s imported oil came from the Middle East, predominantly Saudi Arabia and the UAE. The above facts are enough to discern the critical significance of the Middle Eastern region for Japan. For Japan to have an unhindered supply o
Hindutva, the core political ideology of India’s current ruling party, the Bharatiya Janata Party (BJP), seeks to transform constitutionally secular India into a Hindu Rashtra (“Hindu nation”). Although Hindutva has all of the features of right-wing extremism (RWE), it is nevertheless viewed as an insular sociopolitical phenomenon, due to the Eurocentric nature of RWE discourse. Recent theoretical and analytical research has sought to showcase the similarity between RWE and Hindutva, but empiric
Cybersecurity is becoming indispensable for everyone and everything in the times of the Internet of Things (IoT) revolution. Every aspect of human society — be it political, financial, technological, or cultural — is affected by cyber-attacks or incidents in one way or another. Newspapers are an excellent source that perfectly captures this web of cybersecurity. By implementing various NLP techniques such as tf-idf, word embedding and sentiment analysis (SA) (machine learning method), this resea
Machine Learning (ML) and specifically Natural Language Processing (NLP) are increasingly used as tools in the cybersecurity world. These NLP tools bring new capabilities that support both defenders and attackers in their activities, whether it is risk scenarios such as events and threats or security operations. Ours is a unique case study as we are investigating cybersecurity news on a national and global level. This large study covered six countries and 18 major newspapers and analyzed thousan
The rapid advancement and widespread use of Large Language Models (LLMs) have raisedconcerns about their potential to generate persuasive and deceptive content at scale. As LLM-generated text becomes increasingly indistinguishable from human writing, identifying linguisticfeatures in LLM-generated fake news is critical for both the detection and mitigation of fakenews. This research examines linguistic differences between real news and LLM-generated fakenews headlines across four dimensions: tox
Hindutva, the core political ideology of India's current ruling party, the Bharatiya Janata Party (BJP), seeks to transform constitutionally secular India into a Hindu Rashtra (`Hindu nation'). Although Hindutva has all of the features of right-wing extremism (RWE), it is nevertheless viewed as an insular sociopolitical phenomenon due to the Eurocentric nature of RWE discourse. Recent theoretical and analytical research has sought to showcase the similarity between RWE and Hindutva, whereas empi
The increasing polarization within India’s media landscape necessitates empirical investigation into how legacy and digital media differ in content strategies and audience engagement. This study examines the distinct operational patterns between legacy and digital media in India’s increasingly polarized news landscape. Using computational methods, we analyzed 1,074 YouTube news videos and over 400,000 user comments to address critical research gaps in understanding how institutional origins shap
Open papers in the app to read, cite, and organize with AI.