{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,8,2]],"date-time":"2025-08-02T17:35:01Z","timestamp":1754156101613,"version":"3.41.2"},"reference-count":34,"publisher":"Emerald","issue":"4","license":[{"start":{"date-parts":[[2017,11,6]],"date-time":"2017-11-06T00:00:00Z","timestamp":1509926400000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.emerald.com\/insight\/site-policies"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IJWIS"],"published-print":{"date-parts":[[2017,11,6]]},"abstract":"<jats:sec>\n<jats:title content-type=\"abstract-subheading\">Purpose<\/jats:title>\n<jats:p>The purpose of this paper is to clarify the characteristics of growth users over a long time to strategically collect a large amount of specific users\u2019 tweets. Twitter reflects events and trends in users\u2019 real lives because many of them post tweets related to their experiences. Many studies have succeeded in detecting events along with real-life information from a large amount of tweets by assuming users as social sensors. To collect a large amount of tweets based on specific users for successful Twitter studies, the authors have to know the characteristics of users who are active over long periods of time.<\/jats:p>\n<\/jats:sec>\n<jats:sec>\n<jats:title content-type=\"abstract-subheading\">Design\/methodology\/approach<\/jats:title>\n<jats:p>The authors explore the status of users who were active in 2012, and classify users into three statuses of Dead, Lock and Alive. Based on the differences between the numbers of tweets in 2012 and 2016, the authors further classify Alive users into three types of Eraser, Slumber and Growth. The authors analyze the characteristic feature values observed in each user behavior and provide interesting findings with each status\/type based on Gaussian mixture model clustering and point-wise mutual information.<\/jats:p>\n<\/jats:sec>\n<jats:sec>\n<jats:title content-type=\"abstract-subheading\">Findings<\/jats:title>\n<jats:p>From their sophisticated experimental evaluations, the authors found that active users more easily dropped out than inactive users, and users who engaged in reciprocal communications often became Growth type. Also, the authors found that active users and users who were not retweeted by other users often became Eraser type. The authors\u2019 proposed methods effectively predicted Growth\/Eraser-type users compared with the logistic regression model. From these results, the authors clarified the effectiveness of five feature values per active hour to detect intended Twitter user growth for strategically collecting a large amount of tweets.<\/jats:p>\n<\/jats:sec>\n<jats:sec>\n<jats:title content-type=\"abstract-subheading\">Originality\/value<\/jats:title>\n<jats:p>The authors focus on user growth prediction. To appropriately estimate users who have potential for growth, they collect a large amount of users and explore their status and growth after three years. The research quantitatively clarifies the characteristics of growth users by clustering using robust feature values and provides interesting findings obtained by analysis. After that, the authors propose an effective prediction method for growth users and evaluate the effectiveness of their proposed method.<\/jats:p>\n<\/jats:sec>","DOI":"10.1108\/ijwis-04-2017-0034","type":"journal-article","created":{"date-parts":[[2017,10,3]],"date-time":"2017-10-03T19:12:43Z","timestamp":1507057963000},"page":"370-386","source":"Crossref","is-referenced-by-count":2,"title":["Twitter user growth analysis based on diversities in posting activities"],"prefix":"10.1108","volume":"13","author":[{"given":"Shuhei","family":"Yamamoto","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Kei","family":"Wakabayashi","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Tetsuji","family":"Satoh","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yuri","family":"Nozaki","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Noriko","family":"Kando","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"140","reference":[{"volume-title":"Selected Papers of Hirotugu Akaike","year":"1998","key":"key2020120416381539700_ref001"},{"first-page":"1568","article-title":"Twitter catches the flu: detecting influenza epidemics using Twitter","year":"2011","key":"key2020120416381539700_ref002"},{"first-page":"450","article-title":"Modeling public mood and emotion: Twitter sentiment and socio-economic phenomena","year":"2011","key":"key2020120416381539700_ref003"},{"first-page":"53","article-title":"Exploiting new sentiment-based meta-level features for effective sentiment analysis","year":"2016","key":"key2020120416381539700_ref004"},{"first-page":"10","article-title":"Measuring user influence in Twitter: the million follower fallacy","year":"2010","key":"key2020120416381539700_ref005"},{"first-page":"1409","article-title":"Rhythms in Twitter","year":"2011","key":"key2020120416381539700_ref006"},{"first-page":"61","article-title":"Antisocial behavior in online discussion communities","year":"2015","key":"key2020120416381539700_ref007"},{"issue":"1","key":"key2020120416381539700_ref008","first-page":"22","article-title":"Word association norms, mutual information, and lexicography","volume":"16","year":"1990","journal-title":"Computational Linguistics"},{"issue":"1","key":"key2020120416381539700_ref009","first-page":"215","article-title":"The regression analysis of binary sequences (with discussion)","volume":"20","year":"1958","journal-title":"Journal of the Royal Statistical Society B"},{"first-page":"307","article-title":"No country for old members: User lifecycle and linguistic change in online communities","year":"2013","key":"key2020120416381539700_ref010"},{"first-page":"829","article-title":"Churn prediction in new users of yahoo! Answers","year":"2012","key":"key2020120416381539700_ref011"},{"key":"key2020120416381539700_ref012","unstructured":"Edwards, J. (2015), \u201cTwitter\u2019s user growth problem may be worse than you think\u201d, available at: http:\/\/uk.businessinsider.com\/twitter-user-growth-is-worse-than-you-think-2015-2 (accessed 30 April 2017)."},{"key":"key2020120416381539700_ref013","unstructured":"Ghosh, R. Surachawala, T. and Lerman, K. (2011), \u201cEntropy-based classification of \u2018retweeting\u2019 activity on Twitter\u201d, paper presented at KDD workshop on Social Network Analysis, 21 August, San Diego, available at: http:\/\/arxiv.org\/abs\/1106.0346 (accessed 30 April 2017)."},{"first-page":"140","article-title":"Characterizing silent users in social media communities","year":"2015","key":"key2020120416381539700_ref014"},{"issue":"4","key":"key2020120416381539700_ref015","doi-asserted-by":"crossref","first-page":"653","DOI":"10.1007\/s11390-010-9355-8","article-title":"Dirichlet process Gaussian mixture models: Choice of the base distribution","volume":"25","year":"2010","journal-title":"Journal of Computer Science and Technology"},{"issue":"2","key":"key2020120416381539700_ref016","first-page":"1","article-title":"Profile characteristics of fake Twitter accounts","volume":"3","year":"2016","journal-title":"Big Data & Society"},{"first-page":"56","article-title":"Why we Twitter: understanding microblogging usage and communities","year":"2007","key":"key2020120416381539700_ref017"},{"first-page":"423","article-title":"Churn prediction in mmorpgs: a social influence based approach","year":"2009","key":"key2020120416381539700_ref018"},{"key":"key2020120416381539700_ref019","unstructured":"Koh, Y. (2014), \u201cOnly 11 per cent of new Twitter users in 2012 are still tweeting\u201d, available at: http:\/\/blogs.wsj.com\/digits\/2014\/03\/21\/new-report-spotlights-twitters-retention-problem\/ (accessed 30 April 2017)."},{"first-page":"182","article-title":"Twitter bursts: analysis of their occurrences and classifications","year":"2014","key":"key2020120416381539700_ref020"},{"first-page":"913","article-title":"The bursty dynamics of the Twitter information network","year":"2014","key":"key2020120416381539700_ref021"},{"first-page":"278","article-title":"Modeling response time in digital human communication","year":"2015","key":"key2020120416381539700_ref022"},{"key":"key2020120416381539700_ref023","unstructured":"Prosser, J. (2016), \u201cTwitter to announce fourth quarter and fiscal year 2015 results\u201d, available at: https:\/\/investor.twitterinc.com\/releasedetail.cfm?ReleaseID=948875 (accessed 30 April 2017)."},{"first-page":"97","article-title":"Sarcasm detection on Twitter: a behavioral modeling approach","year":"2015","key":"key2020120416381539700_ref024"},{"first-page":"851","article-title":"Earthquake shakes Twitter users: real-time event detection by social sensors","year":"2010","key":"key2020120416381539700_ref025"},{"first-page":"87","article-title":"Negative link prediction in social media","year":"2015","key":"key2020120416381539700_ref026"},{"key":"key2020120416381539700_ref027","unstructured":"Twitter Inc (2014), \u201cTwitter reports fourth quarter and fiscal year 2013 results\u201d, available at: https:\/\/investor.twitterinc.com\/releasedetail.cfm?ReleaseID=823321 (accessed at 30 April 2017)."},{"first-page":"1331","article-title":"Whom to mention: Expand the diffusion of tweets by @ recommendation on micro-blogging systems","year":"2013","key":"key2020120416381539700_ref028"},{"issue":"4","key":"key2020120416381539700_ref029","doi-asserted-by":"crossref","first-page":"363","DOI":"10.1108\/IJWIS-04-2014-0014","article-title":"Behavior analysis methods for Twitter users based on transitions in posting activities","volume":"10","year":"2014","journal-title":"International Journal of Web Information Systems"},{"first-page":"513","article-title":"Patterns in interactive tagging networks","year":"2015","key":"key2020120416381539700_ref030"},{"first-page":"523","article-title":"Hierarchical estimation framework of multi-label classifying: a case of tweets classifying into real life aspects","year":"2015","key":"key2020120416381539700_ref031"},{"first-page":"351","article-title":"Comparing information diffusion structure in weblogs and microblogs","year":"2010","key":"key2020120416381539700_ref032"},{"first-page":"3","article-title":"Who will reply to\/retweet this tweet? The dynamics of intimacy from online social interactions","year":"2016","key":"key2020120416381539700_ref033"},{"first-page":"64","article-title":"Who are growth users? Analyzing and predicting intended Twitter user growth","year":"2016","key":"key2020120416381539700_ref034"}],"container-title":["International Journal of Web Information Systems"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.emerald.com\/insight\/content\/doi\/10.1108\/IJWIS-04-2017-0034\/full\/xml","content-type":"application\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/www.emerald.com\/insight\/content\/doi\/10.1108\/IJWIS-04-2017-0034\/full\/html","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,7,24]],"date-time":"2025-07-24T22:23:59Z","timestamp":1753395839000},"score":1,"resource":{"primary":{"URL":"http:\/\/www.emerald.com\/ijwis\/article\/13\/4\/370-386\/166609"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2017,11,6]]},"references-count":34,"journal-issue":{"issue":"4","published-print":{"date-parts":[[2017,11,6]]}},"alternative-id":["10.1108\/IJWIS-04-2017-0034"],"URL":"https:\/\/doi.org\/10.1108\/ijwis-04-2017-0034","relation":{},"ISSN":["1744-0084"],"issn-type":[{"type":"print","value":"1744-0084"}],"subject":[],"published":{"date-parts":[[2017,11,6]]}}}