S
Stephen Kelly
Researcher at Trinity College, Dublin
Publications - 13
Citations - 137
Stephen Kelly is an academic researcher from Trinity College, Dublin. The author has contributed to research in topics: Financial market & Social media. The author has an hindex of 8, co-authored 13 publications receiving 113 citations.
Papers
More filters
Journal ArticleDOI
Estimating the impact of domain-specific news sentiment on financial assets
Stephen Kelly,Khurshid Ahmad +1 more
TL;DR: A method and implementation is presented that analyses the content of news using multiple dictionaries that accounts for the specific use of terminology in a given domain and finds that incorporating news sentiment into a trading strategy increases annual returns over a simple buy and hold strategy for both markets.
Journal ArticleDOI
Distributed morality, privacy, and social media in natural disaster response
Paul Hayes,Stephen Kelly +1 more
TL;DR: It is argued that the delegation of tasks to autonomous computational artefacts in order to partially mitigate this by using representation to remind emergency managers that action is required (for instance, deletion or anonymization of personal data) is one possible component of a solution.
Mining Multimodal Information on Social Media for Increased Situational Awareness.
TL;DR: A system for the real-time extraction of information from text and image content in Twitter messages and combine the spatio-temporal metadata of the messages to filter the data stream for emergency events and visualize the output on an interactive map is described.
Journal ArticleDOI
Bonferroni Mean With Weighted Interaction
TL;DR: The Bonferroni mean with weighted interaction is introduced and a system for emergency management that is able to raise an alarm in the case where certain criteria are met is designed.
Proceedings ArticleDOI
Integration of text and image analysis for flood event image recognition
Min Jing,Bryan Scotney,Sonya Coleman,Martin McGinnity,Xiubo Zhang,Stephen Kelly,Khurshid Ahmad,Antje Schlaf,Sabine Grunder-Fahrer,Gerhard Heyer +9 more
TL;DR: A novel framework in which the rich information available from social media is incorporated with image analysis to enhance image retrieval for disaster management and demonstrates the improved performance of image recognition after incorporating the text features.