TrendMiner (Large-scale, Cross-lingual Trend Mining and Summarisation of Real-time Media Streams) deals with the recent massive growth in online media and the rise of user-authored content (e.g weblogs, Twitter, Facebook) that has lead to challenges of how to access and interpret these strongly multilingual data, in a timely, efficient, and affordable manner. Scientifically, streaming online media pose new challenges, due to their shorter, noisier, and more colloquial nature. Moreover, they form a temporal stream strongly grounded in events and context. Consequently, existing language technologies fall short on accuracy, scalability and portability.
This project is co-funded by the EU under FP7 (Seventh Framework Programme) in research objective ICT-2011.4.2 Language Technologies, target outcome b) Information access and mining.
Contact: Marin Dimitrov
Project Overview
The goal of this project is to deliver innovative, portable open-source real-time methods for cross-lingual mining and summarisation of large-scale stream media.
TrendMiner achieves this through an inter-disciplinary approach, combining deep linguistic methods from text processing, knowledge-based reasoning from web science, machine learning, economics, and political science. No expensive human annotated data is required due to our use of time-series data (e.g. financial markets, political polls) as a proxy. A key novelty is weakly supervised machine learning algorithms for automatic discovery of new trends and correlations. Scalability and affordability are addressed through a cloud-based infrastructure for real-time text mining from stream media.
Results are validated in two high-profile case studies:
- Financial decision support (with analysts, traders, regulators, and economists)
- Political analysis and monitoring (with politicians, economists, and political journalists)
The techniques are generic with many business applications: business intelligence, customer relations management, community support. The project also benefits society and ordinary citizens by enabling enhanced access to government data archives, summarisation of online health information, and tracking of hot societal issues.
Ontotext’s Role
- Multi-paradigm semantic search
- Cross-lingual UI for trend and sentiment exploration and browsing
- TrendMiner platform for real-time stream media collection, analysis and storage
- Large-scale distributed stream processing
- Sequential computation for real-time Machine Learning
- Machine Learning and Text Mining with GPU/CUDA (Compute Unified Device Architecture)