Event threading within news topics

Abstract

With the overwhelming volume of online news available today, there is an increasing need for automatic techniques to analyze and present news to the user in a meaningful and efficient manner. Previous research focused only on organizing news stories by their topics into a flat hierarchy. We believe viewing a news topic as a flat collection of stories is too restrictive and inefficient for a user to understand the topic quickly.In this work, we attempt to capture the rich structure of events and their dependencies in a news topic through our event models. We call the process of recognizing events and their dependencies event threading. We believe our perspective of modeling the structure of a topic is more effective in capturing its semantics than a flat list of on-topic stories.We formally define the novel problem, suggest evaluation metrics and present a few techniques for solving the problem. Besides the standard word based features, our approaches take into account novel features such as temporal locality of stories for event recognition and time-ordering for capturing dependencies. Our experiments on a manually labeled data sets show that our models effectively identify the events and capture dependencies among them.

i-JEN: Visual Interactive Malaysia Crime News Retrieval System

“…In the context of Topic Detection and Tracking (TDT) which is an area aims to effectively retrieve and organise broadcast news (speech) and newswire stories (text) into groups of events, Nallapati et al [16] have modelled the news topic based on event and their dependency. They named the process of recognizing events and identifying dependencies among them as event threading, an analogy to email threading that shows connections between related email messages.…”

STORIES in Time: A Graph-Based Interface for News Tracking and Discovery

“…[2], [3], [4], [5], topic detection and tracking (TDT) [6], [7], [8], burstiness [9], [10], [11], [12], and various summarisation approaches using co-occurrence, such as [10], [13]. We aim at more flexible content sub-structures than the fixed "topics" of TTM and TDT and apply measures of burstiness and co-occurrence to characterise these.…”

“…8 Evaluations of search quality [1] demonstrated that the STORIES search finds coherent subsets of documents, that its quality is comparable to or better than state-of-the-art clustering, and that the tool enables people to answer questions on ground-truth events accurately and quickly.…”

FISER: An Effective Method for Detecting Interactions between Topic Persons

“…For instance, Chen and Chen [4] summarized the incidents of a topic timeline to help readers understand the story of a topic quickly. Basically, a topic is associated with specific times, places, and persons [11]. Discovering the interactions between the persons can help readers construct the background of the topic and facilitate document comprehension.…”