Educational Videos Subtitles’Summarization Using Latent Dirichlet Allocation and Length Enhancement
作者机构:Department of Information TechnologyCollege of ComputerQassim UniversityBuraydah51452Saudi Arabia
出 版 物:《Computers, Materials & Continua》 (计算机、材料和连续体(英文))
年 卷 期:2022年第70卷第3期
页 面:6205-6221页
核心收录:
学科分类:1205[管理学-图书情报与档案管理] 08[工学] 0835[工学-软件工程] 0714[理学-统计学(可授理学、经济学学位)] 0701[理学-数学] 0812[工学-计算机科学与技术(可授工学、理学学位)]
主 题:Subtitle summarization educational videos topic modelling LDA extractive summarization
摘 要:Nowadays,people use online resources such as educational videos and ***,such videos and courses are mostly long and thus,summarizing them will be *** video contents(visual,audio,and subtitles)could be analyzed to generate textual summaries,i.e.,***’subtitles contain significant ***,summarizing subtitles is effective to concentrate on the necessary *** of the existing studies used Term Frequency-Inverse Document Frequency(TF-IDF)and Latent Semantic Analysis(LSA)models to create lectures’*** study takes another approach and applies LatentDirichlet Allocation(LDA),which proved its effectiveness in document ***,the proposed LDA summarization model follows three *** first phase aims to prepare the subtitle file for modelling by performing some preprocessing steps,such as removing stop *** the second phase,the LDA model is trained on subtitles to generate the keywords list used to extract important *** in the third phase,a summary is generated based on the keywords *** generated summaries by LDA were lengthy;thus,a length enhancement method has been *** the evaluation,the authors developed manual summaries of the existing“EDUVSUMeducational videos *** authors compared the generated summaries with the manual-generated outlines using two methods,(i)Recall-Oriented Understudy for Gisting Evaluation(ROUGE)and(ii)human *** performance of LDA-based generated summaries outperforms the summaries generated by TF-IDF and *** reducing the summaries’length,the proposed length enhancement method did improve the summaries’precision *** domains,such as news videos,can apply the proposed method for video summarization.