عنوان المقالة:تحسين واجهة إكتشاف وتتبع المواضيع التفاعلية باستخدام منهجية حقيبة الكلمات و الكيانات المسماة An Enhanced Interactive Topic Detection and Tracking Interface using Bag of words and Named Entities Approach.
عمر مبروك عوض باشداده | Omar Mabrook Awadh Bashaddadh | 3684
Publication Type
Master Thesis
Arabic Authors
عمر مبروك عوض باشداده
English Authors
Omar Mabrook A. Bashaddadh
Abstract
كتاب الرسألة-مكتبة الجامعة الوطنية الماليزية(UKM)
Abstract
Interactive Topic Detection and Tracking (iTDT) refers to Topic Detection and Tracking (TDT), which focuses on user interaction, user evaluation, and user interfaces. Recently, increasing effort has been devoted to user interfaces to improve TDT systems by investigating not just the user interaction aspect but also user and task oriented evaluation. (This study investigates the effectiveness and usefulness of the bag of words and named entities approaches implemented in a well-designed iTDT interface called Interactive Event Tracking (iEvent) including what TDT tasks are these approaches facilitating). iEvent is composed of three components, which are Cluster View (CV), Document View (DV) and Term View (TV). User experiment was carried out 120 tasks amongst journalists. 50% of these tasks were tracking and the remaining were detection to compare three settings of iEvent: Setup 1 and Setup 2 (baseline setups) and Setup 3 (experimental setup). Setup 1 used bag of words; Setup 2 used named entities while Setup 3 use a combination of bag of words and named entities. Journalists were asked to perform TDT tasks; Tracking and Detections. Findings revealed that 98.33% (tracking) and 83.33% (Detection) tasks were conduct successfully. Moreover, the combination of bag of words and named entities approaches generally facilitated the journalists to perform well in the TDT tasks, with 90% of them expressed their satisfaction and interesting in iEvent in both tasks. Therefore the use of bag of words and named entities in iTDT are useful, and enhanced the effectiveness of users’ performance in performing the TDT tasks. 90% of participants in the tracking task and 73% in the Detection task found setup 3 was easy, useful and interesting.
Publication Date
8/24/2011
Publisher
FAKULTI TEKNOLOGI DAN SAINS MAKLUMAT UNIVERSITI KEBANGSAAN MALAYSIA BANGI
Volume No
Issue No
Pages
153
File Link
تحميل (95 مرات التحميل)
Keywords
iTDT, iEvent, bag of words, named entities, Event Tracking, Setup, CV, DV, TV, Detection task, TDT
رجوع