Investigating the Combination of Bag of Words and Named Entities Approach in Tracking and Detection Tasks among Journalists

摘要: The proliferation of many interactive Topic Detection and Tracking (iTDT) systems has motivated researchers to design that can track detect news better. iTDT focuses on user interaction, evaluation, interfaces. Recently, increasing effort been devoted interfaces improve TDT by investigating not just the interaction aspect but also task oriented evaluation. This study investigates combination bag words named entities approaches implemented in interface, called Interactive Event (iEvent), including what tasks these facilitate. iEvent is composed three components, which are Cluster View (CV), Document (DV), Term (TV). User experiments have carried out amongst journalists compare settings iEvent: Setup 1 2 (baseline setups), 3 (experimental setup). used entities, while a entities. Journalists were asked perform tasks: Detection. Findings revealed generally facilitated well tasks. confirmed approach useful enhanced effectiveness users’ performance performing It gives suggestions features with their