2024-03-30T00:53:04Zhttps://ipsj.ixsq.nii.ac.jp/ej/?action=repository_oaipmhoai:ipsj.ixsq.nii.ac.jp:001024702024-03-29T05:26:34Z01164:01165:07638:07639
Domain-Level Cross-Social Media Context AggregationDomain-Level Cross-Social Media Context Aggregationengソーシャルメディアhttp://id.nii.ac.jp/1001/00102447/Technical Reporthttps://ipsj.ixsq.nii.ac.jp/ej/?action=repository_action_common_download&item_id=102470&item_no=1&attribute_id=1&file_no=1Copyright (c) 2014 by the Information Processing Society of JapanGraduate School of Information, Production and Systems, Waseda UniversityGraduate School of Information, Production and Systems, Waseda UniversityChamwenga M., ChilufyaMizuho, IwaiharaAggregating content across social media or Social Networking Services (SNS) has the benefit of discovering interesting information that may not be available on a single social media. However, in the face of information overload it becomes imperative to employ fine grained cross-social media aggregation. Social media interaction is characterized by threaded conversations initiated by a post on domain specific topics for example, politics, health or personal life; this creates a post-feedback context. Research on cross-social media aggregation has focused mainly on high-level identification of trending topics, however, providing users with a parallel view of contexts from multiple social media, irrespective of popularity, can realize discovery of related contents with less effort. In this paper, we propose a framework that, given a context on one social media retrieves highly relevant context on another social media by using informative keywords extracted from a given context and special “#” prefixed words called hashtags, while maintaining the premise of being relevant in time.Aggregating content across social media or Social Networking Services (SNS) has the benefit of discovering interesting information that may not be available on a single social media. However, in the face of information overload it becomes imperative to employ fine grained cross-social media aggregation. Social media interaction is characterized by threaded conversations initiated by a post on domain specific topics for example, politics, health or personal life; this creates a post-feedback context. Research on cross-social media aggregation has focused mainly on high-level identification of trending topics, however, providing users with a parallel view of contexts from multiple social media, irrespective of popularity, can realize discovery of related contents with less effort. In this paper, we propose a framework that, given a context on one social media retrieves highly relevant context on another social media by using informative keywords extracted from a given context and special “#” prefixed words called hashtags, while maintaining the premise of being relevant in time.AN10112482研究報告データベースシステム(DBS)2014-DBS-15925162014-07-252014-07-24