Türkçe Paylaşım Yapan Kullanıcılar İçin Sosyal Ağ Tabanlı Analiz ve Tavsiye Sistemi

Kişiler arası bilgi paylaşımında yaygın olarak kullanılan sosyal ağlar, hızla artan kullanıcı sayıları ile iletişimde yeni bir çığır açmıştır. Kullanıcı sayılarındaki artışa bağlı olarak sosyal ağlarda üretilen içeriğin devasa boyutlara ulaşması, gerekli bilgilerin ilgili hedef kitleye ulaşmasını zorlaştırmaktadır. Bu noktada içerik analiz ve filtreleme sistemlerine ihtiyaç doğmaktadır. Bu çalışmada Twitter üzerinde kullanıcıların ilgi alanlarını dinamik olarak analiz eden ve bu doğrultuda takip edilebilecek diğer kullanıcıları tavsiye olarak sunan bir sistem geliştirilmiştir. Sistem tasarımında doğal dil işleme, büyük veri analizi, şartlı olasılık teoremi ve tabu arama yaklaşımlarından yararlanılmıştır. Geliştirilen yazılım Twitter'ı aktif olarak kullanan bir grup ile test edilmiş ve alınan geri bildirimler doğrultusunda sistemin %86 başarılı olduğu ortaya konmuştur.

Social Network Based Analysis and Recommendation System for Users Who Share Turkish Content *1 Onur SEVLİ, 2 Ecir Uğur KÜÇÜKSİLLE

Social networks which are widely used for interpersonal information sharing has opened a new era in communication with rapidly increasing number of users. Depending on the increase in the number of users the generated content has reached huge dimensions, so it is difficult the required information to reach its target audience. At this point a need arises for content analyse and filtering systems. In this study a system has been developed which analyses users' interests dynamically on Twitter and in this direction advices appropriate users that can be followed. In system design natural language processing, big data analysis, conditional probability theorem and tabu search approach were used. The developed software was tested with a group that uses Twitter actively and according to received feedbacks it has been shown the system is %86 successful.

___

  • [1] R. Kalakota, "Sizing 'Mobile + Social' big data stats," Business Analytics 3.0, URL: https://practicalanalytics.co/2012/10/22/sizing-mobilesocial-big-data-stats (Erişim zamanı: Ocak, 10, 2016).
  • [2] T. Aytekin, Tavsiye Sistemleri (Öneri Sistemleri), URL:http://akademik.bahcesehir.edu.tr/~tevfik/tavsiye _sistemle ri_oneri_sistemleri.html(SonErişim:5.5.2015)
  • [3] J. Hannon, M. Bennett, and B. Smyth, "Recommending twitter users to follow using content and collaborative filtering approaches," Fourth ACM conference on Recommender systems, pp. 199-206, (2010).
  • [4] Z. Yu, C. Wang, J. Bu, X. Wang, Y. Wu, and C. Chen, "Friend recommendation with content spread enhancement in social networks," Information Sciences, vol. 309, pp. 102-118, (2015).
  • [5] CC. Chang and KH. Chu, "A Recommender System Combining Social Networks for Tourist Attractions", Fifth International Conference on Computational Intelligence, Communication Systems and Networks, pp. 42-47, (2013).
  • [6] CH. Lee and TF. Chien, "Leveraging microblogging big data with a modified density-based clustering approach for event awareness and topic ranking," Journal of Information Science, vol. 39, no. 4, pp. 523- 543, (2013).
  • [7] ML. Kern, JC. Eichstaedt, HA. Schwartz, G. Park, LH. Ungar, DJ. Stillwell, M. Kosinski, L. Dziurzynski, M. Seligman, "From "Sooo Excited!!!" to "So Proud":Using Language to Study Development", Developmental Psychology, vol. 50 no. 1, pp. 178-188, (2014).
  • [8] LJ. Zhao, YJ. Ren, J. Wang, LS. Meng, CL. Zou, "Research on the Opinion Mining System for Massive Social Media Data", Natural Language Processing And Chinese Computing, vol. 400, pp. 424-431, (2013).
  • [9] R. Compton, C. Lee, TC. Lu, L. De Silva, M. Macy, "Detecting future social unrest in unprocessed Twitter data Emerging Phenomena and Big Data", IEEE International Conference on Intelligence and Security Informatics: Big Data, Emergent Threats, And Decision-Making In Security Informatics, pp. 56-60, (2013).
  • [10] A. Bruns, T. Highfield, and J. Burgess, "The Arab spring and social media audiences," American Behavioral Scientist, vol. 57, no. 7, pp. 871-898, (2013).
  • [11] XT. Vu, MH. Abel, P. Morizet-Mahoudeaux, "A user-centered and groupbased approach for social data filtering and sharing", Computers in Human Behavior, vol. 51, pp. 1012-1023, (2014).
  • [12] L. Wu, N. Luo, "Social streams recommendation in sina microblog with relation of user and interest", IEEE International Conference on Information Science and Technology, pp. 480-483, (2014).
  • [13] S. Puglisi, J. Parra-Arnau, F. Jordi, D. RebolloMonedero, "On contentbased recommendation and user privacy in social-tagging systems" Computer Standards & Interfaces vol. 41, pp. 17-27, (2015).
  • [14] MC. Yang and HC Rim, "Identifying interesting Twitter contents using topical analysis", Expert Systems with Applications, vol. 41, pp. 4330-4336, (2014).
  • [15] D. Kang, D. Han, N. Park, S. Kim, U. Kang, S. Lee, "Eventera: Real-Time Event Recommendation System from Massive Heterogeneous Online Media". IEEE International Conference on Data Mining Workshop, pp. 1211-1214, (2014).
  • [16] I. Uysal and WB. Croft, "User oriented tweet ranking: a filtering approach to microblogs", 20th ACM international conference on Information and knowledge management, 2261-2264, (2011).
  • [17] SJ. Yu, "The dynamic competitive recommendation algorithm" Social network services, vol. 187, pp. 1-14, (2012).
  • [18] AR, Sun, J. Cheng, DD. Zeng, "A novel recommendation framework for micro-blogging based on information diffusion", 19th Annual Workshop on Information Technologies and Systems, (2009).
  • [19] B. Liang, Y. Liu, M. Zhang, S. Ma, L. Ru, K. Zhang, "Searching for people to follow in social networks", Expert Systems with Applications vol. 41, no. 16, pp. 7455-7465, (2014).
  • [20] N. Jamil, AC. Alhadi, SA. Noah, "A collaborative names recommendation in the Twitter environment based on location", In Semantic Technology and Information Retrieval (STAIR) 2011 International Conference on, pp. 119-124, (2011).
  • [21] M. Islam, C. Ding, C. Chi, "Personalized Recommender System on Whom to Follow in Twitter" Big Data and Cloud Computing (BdCloud), IEEE Fourth International Conference on, pp. 326-333, (2014).
  • [22] WJ. Lee, KJ. Oh, CG. Lim, HJ. Choi, "User profile extraction from Twitter for personalized news recommendation", In Advanced Communication Technology (ICACT) 16th International Conference on, pp. 779-783, (2014).
  • [23] H. Lu and C. Lee, "The Topic-Over-Time Mixed Membership Model (TOTMMM): A Twitter Hashtag Recommendation Model that Accommodates for Temporal Clustering Effects", Web Intelligence (WI) and Intelligent Agent Technologies (IAT) 2013 IEEE/WIC/ACM International Joint Conferences on, pp. 21-25, (2015).
  • [24] N. Jonnalagedda and S. Gauch, "Personalized News Recommendation Using Twitter", In Web Intelligence (WI) and Intelligent Agent Technologies (IAT) IEEE/WIC/ACM International Joint Conferences on, pp. 21-25, (2013).
  • [25] ME. Babacan, İ. Haşlak, İ. Hira, "Sosyal Medya ve Arap Baharı", Akademik İncelemeler Dergisi, 6(2), 63- 91, (2011).
  • [26] YE., Sarıgül, "Sosyal Medya Nedir?", Sosyal Pedia, URL: http://www.sosyalpedia.com/sosyalmedya-nedir-1 (Erişim zamanı: Mart, 18, 2015).
  • [27] S. Tezgüler, "Sosyal Medya Nedir?", URL: sosyalmedyakulubu.com.tr/sosyalmedya/sosyalmedya-nedir.html (Erişim zamanı: Şubat, 3, 2015).
  • [28] S. Barutçu ve M. Tomaş, "Sürdürülebilir Sosyal Medya Pazarlaması Ve Sosyal Medya Pazarlaması Etkinliğinin Ölçümü" Journal of Internet Applications & Management/İnternet Uygulamaları ve Yönetimi Dergisi, 4(1), (2013).
  • [29] S. Eyidilli, "Twitter'ın aylık aktif kullanıcı sayısı 316 milyona yükseldi", Webrazzi, URL: http://webrazzi.com/2015/07/29/twitterin-aylik-aktifkullanici-sayisi-316-milyon (Erişim zamanı: Eylül, 4, 2015).
  • [30] B. Kaya, "Sosyal Ağ Modelleme Kullanılarak Tıbbi Veri Ağında Bağlantı Tahmini Yöntemleri", Doktora tezi, Fırat Üniversitesi Fen Bilimleri Enstitüsü, Elazığ, 2015.
  • [31] Ö. Özgöbek ve RC. Erdur, "Öneri Sistemleri ve Bir Uygulama Alanı Olarak Haber Öneri Sistemleri", Akademik Bilişim Konferansları, Eskişehir, 31 Ocak-6 Şubat 2015.
  • [32] H. Jafarkarimi, ATH. Sim, R. Saadatdoost, "A naive recommendation model for large databases" International Journal of Information and Education Technology, vol. 2, no. 3, pp. 216, (2012).
  • [33] ZemberekNlp, "Zemberek Nasıl Çalışır?", URL: http://zembereknlp.blogspot.com.tr/2007_04_01 _archive.html (Erişim zamanı: Nisan, 27, 2014).
  • [34] R. Usta, "Naïve Bayes Sınıflandırma Algoritması", URL: http://kodcu.com/2014/05/naive-bayessiniflandirma-algoritmasi (Erişim zamanı: Haziran, 24, 2015)