Content-based Social Media Archive Archiving Research

With the development and popularization of information technology and mobile data,social media has become the main platform for information production,distribution,communication and communication,and has become an indispensable part of our daily life.Social media information records the daily behavior of the public,reflecting the current state of society,where valuable information can be stored as a long-term storage of social media archives because it is a social memory and an important part of human cultural heritage.However,social media information has the characteristics of fast update speed and short life cycle,which makes it easy to be lost and generated while being transmitted quickly,so that much social media information is not effectively stored.Collecting and storing valuable social media information is of great significance to the long-term storage and permanent acquisition of human cultural heritage,and has become the focus of both the theoretical and practical circles.At present,there are projects for collecting and storing Internet resources at home and abroad,but these projects pay more attention to political information resources and pay less attention to social media information resources.In addition,when collecting information at home and abroad,the link of the website that needs to be collected is stored on the server.In this organization mode,the user can only use the archive resource through the URL search,if the user knows less about the information to be queried.,then you won't be able to get the content you want.This is different from the current user's habit of searching through keywords and keywords.This article describes the related issues from the perspective of social media archive content.The main contents are:(1)Through the inductive analysis of the research hotspots of academic network information resources in recent years,it concludes that the current research on the collection of social media archives with content as the research object is weak.It analyzes the attributes of social media information,defines the concept of social media archives,clarifies the theory and principles of archive archiving,and provides corresponding theoretical support for the subsequent main parts.(2)The third chapter introduces the main body,scope,cycle,method,technology and strategy of social media files.Firstly,the cooperation mode of the collection subject is analyzed and determined.Secondly,based on the traditional file collection method,combined with the characteristics of social media,the social media file collection method is organized;again,according to the factors affecting the scope,cycle,technology and strategy.Determine the scope,cycle,technology,and strategy of social media archive collection.(3)Chapter 4 details three aspects of social media information processing,including information filtering,semantic analysis and value identification.Since social media information is often copied and shared,the collected information may be redundant and need to be filtered;since social media information includes various tags,expressions,and other non-plain text information as well as social media information,usually It is not a phrase,but a long sentence.Such information is not recognized by the computer.Therefore,it needs to be semantically processed and converted into a computer-readable language.Finally,through the identification of social media files,the valueless information is eliminated.(4)The storage of social media files is the last link of archiving,and it is also the most important link.The quality of storage will directly affect the satisfaction of users in using files.The fifth part introduces the storage of social media files from the perspective of storage carrier,storage strategy and storage process selection.At the end of the paper,the research done in this paper is summarized,and the future research is prospected,which points out the ideas and directions for the later research.