Extracting hierarchical structure of content groups from different social media platforms using multiple social metadata

Abstract

A novel scheme for retrieving users' desired contents, i.e., contents with topics in which users are interested, from multiple social media platforms is presented in this paper. In existing retrieval schemes, users first select a particular platform and then input a query into the search engine. If users do not specify suitable platforms for their information needs and do not input suitable queries corresponding to the desired contents, it becomes difficult for users to retrieve the desired contents. The proposed scheme extracts the hierarchical structure of content groups (sets of contents with similar topics) from different social media platforms, and it thus becomes feasible to retrieve desired contents even if users do not specify suitable platforms and do not input suitable queries. This paper has two contributions: (1) A new feature extraction method, Locality Preserving Canonical Correlation Analysis with multiple social metadata (LPCCA-MSM) that can detect content groups without the boundaries of different social media platforms is presented in this paper. LPCCA-MSM uses multiple social metadata as auxiliary information unlike conventional methods that only use content-based information such as textual or visual features. (2) The proposed novel retrieval scheme can realize hierarchical content structuralization from different social media platforms. The extracted hierarchical structure shows various abstraction levels of content groups and their hierarchical relationships, which can help users select topics related to the input query. To the best of our knowledge, an intensive study on such an application has not been conducted; therefore, this paper has strong novelty. To verify the effectiveness of the above contributions, extensive experiments for real-world datasets containing YouTube videos and Wikipedia articles were conducted.

Ranking of Importance Measures of Tweet Communities: Application to Keyword Extraction From COVID-19 Tweets in Japan

“…Using G, we detect tweet communities with similar topics. Following the reports that the Louvain method [32] works well for multimedia content clustering [9], [11], [33], [34], we apply the Louvain method [32] to G. The Louvain method is based on a quality measure of community detection results called modularity [35]. The modularity Q is defined as…”

“…Using \documentclass[12pt]{minimal} \usepackage{amsmath} \usepackage{wasysym} \usepackage{amsfonts} \usepackage{amssymb} \usepackage{amsbsy} \usepackage{upgreek} \usepackage{mathrsfs} \setlength{\oddsidemargin}{-69pt} \begin{document} }{}$G$ \end{document} , we detect tweet communities with similar topics. Following the reports that the Louvain method [32] works well for multimedia content clustering [9] , [11] , [33] , [34] , we apply the Louvain method [32] to \documentclass[12pt]{minimal} \usepackage{amsmath} \usepackage{wasysym} \usepackage{amsfonts} \usepackage{amssymb} \usepackage{amsbsy} \usepackage{upgreek} \usepackage{mathrsfs} \setlength{\oddsidemargin}{-69pt} \begin{document} }{}$G$ \end{document} . The Louvain method is based on a quality measure of community detection results called modularity [35] .…”

Consensus Clustering of Tweet Networks via Semantic and Sentiment Similarity Estimation

“…• If many search results were returned for each query, we obtained only 300 tweets. We set the ground truth labels for each tweet as the queries used for crawling them, in reference to [57]. Note that we exclude terms in queries from the calculation of textual features described in Section III-A for fair evaluation.…”

Music Video Recommendation Based on Link Prediction Considering Local and Global Structures of a Network

“…Finally, we define link weights w(p (x) , q (y) ) of f p (x) ,q (y) based on similarities of the music video features and the user features. In the proposed method, we define similarities based on the following equation, which is effective for constructing a network for which nodes are contents on social media [78], [79].…”