IRAug 24, 2016

Sedano: A News Stream Processor for Business

arXiv:1608.06876v1
Originality Synthesis-oriented
AI Analysis

This system addresses the need for efficient business intelligence tools by enabling users to retrieve and filter news about specific companies, though it appears incremental as it builds on existing stream processing and entity-linking techniques.

The authors tackled the problem of processing and indexing continuous streams of business news by developing Sedano, a system that analyzes and enriches news items through entity-linking and classification phases, resulting in a scalable and fault-tolerant architecture deployable on commodity machines.

We present Sedano, a system for processing and indexing a continuous stream of business-related news. Sedano defines pipelines whose stages analyze and enrich news items (e.g., newspaper articles and press releases). News data coming from several content sources are stored, processed and then indexed in order to be consumed by Atoka, our business intelligence product. Atoka users can retrieve news about specific companies, filtering according to various facets. Sedano features both an entity-linking phase, which finds mentions of companies in news, and a classification phase, which classifies news according to a set of business events. Its flexible architecture allows Sedano to be deployed on commodity machines while being scalable and fault-tolerant.

Foundations

The foundational work for this paper's niche, ranked by how specifically the neighbourhood builds on it — not by global fame.

Your Notes