Research On The Method Of Improving The Social Popularity Of Video Based On YouTube

With the rapid development of social media,video sharing sites like YouTube,YouKu are getting more and more attention,more people are willing to spend longer time on the social media.The social media has changed people's lifestyle and brought the social marketing.Enterprises,organizations and individuals hope to attract high social popularity by uploading content onto social media platforms,since higher popularity usually indicates stronger influence,more widely known and even higher revenue.Therefore,mining the data of social media,analysing the valuable information,extracting the potential rule,studying how to improve the popularity of social media has become a hot topic of concern for many researchers.In this paper,we study the current development of social media and the related technology theory.According to the YouTube data,the video view growth pattern is analyzed.Based on the results of data analysis,this paper puts forward a new method to improve the social attention of video.The main works of the paper are listed as follows:(1)In this paper,we analyze two aspects about video view growth pattern of YouTube videos.Firstly,the pattern of aggregated view is studied.It is found that the aggregated view rate peaks in the first few days,and falls quickly in the following days,and then decrease slowly during the consecutive weeks.Finally,the view rate tends to be a constant on the long run.The aggregated view count after a period of two months can be fitted with a linear line.Secondly,the view growth pattern of individual video is explored.The results indicate that the majority of videos peak at the very beginning of videos' lifetime,and the category of view sources causes the peak is different.The view count of individual video and the view count from each source item also stabilize after a period of two months.(2)Through the analysis of view growth pattern video view growth pattern of YouTube videos,this paper learned that the search engine and recommendation system is the most important source of the video attention.In addition,the title and the tags of the video are the most important text information to describe the video content,and it is the important basis for the user to decide whether to click the video.Based on these conclusion,this paper proposes a method that suggests keywords for video uploaders to refine titles and tags of their videos and then to gain higher popularity.The method generates candidate keywords by applying both semantic analysis of original tags and video content recognition.On one hand,taking the original keywords of a video as input,the method applies the WordNet semantic search to gain the most relevant words and collects related video titles from the three top video sharing sites(YouTube,Yahoo Video,Bing Video).On the other hand,through recognizing video content with deep learning technology,the method extracts the entity name of video content as candidates.Finally,a TF-SIM algorithm is proposed to sort the generated keywords and the most relevant keywords are recommended to uploaders for optimizing the titles and tags of their videos.(3)The proposed method is evaluated using dataset from three aspects:professional website,user and YouTube,respectively.It is demonstrated that the video title and tags optimized with our method can attract more popularity and longer viewing time per playback.This result shows that the TF-SIM algorithm is effective.