GÜNLÜK SOSYAL MEDYA KULLANICI HAREKETLİLİK VERİLERİNDEN ANORMAL AKTİVİTELERİN TESPİTİ

Anormal aktiviteler, insanlar veya nesnelerin normal ve rutin davranışlarına uymayan aktiviteleri ifade etmektedir. Sosyal ağlardan anormal aktivite, hesap veya paylaşımların tespiti, sosyal medya kullanıcılarını zararlı ve rahatsız edici içeriklerden uzak tutmak için önem taşımaktadır. Ancak anormal aktivitelerin tespiti, anormal aktivitelerin gerçek olanlardan ayrılmasının zor olması, mevcut algoritmalar ve değerlendirme ölçütlerinin yetersiz olması, sosyal medya büyük verisinin analizinin zorlukları ve mekânsal ve zamansal boyutların ele alınmasının zorluklarından dolayı zordur. Bu çalışmada günlük sosyal medya kullanıcı hareketlilik verisi üzerinden anormal aktivitelerin tespiti yapılmıştır. Ayrıntılı olarak, sosyal medya kullanıcı hareketliliklerinden, günlük toplam ziyaret edilen lokasyon sayısı ve günlük toplam uzaklık adında iki özellik çıkarılmış ve bu özellikler anormal aktivitelerin tespitinde kullanılmıştır. Anormal aktivitelerin tespiti için DBSCAN kümeleme algoritmasını kullanan bir algoritma önerilmiştir. Elde edilen sonuçlar önerilen algoritmanın sosyal medya kullanıcılarının normal günlük aktivitelerini öğrenebildiğini ve anormal aktiviteleri tespit edebildiğini göstermiştir.

Anahtar Kelimeler:

anormal aktivite tespiti, sosyal ağlar, mekânsal sosyal medya madenciliği, DBSCAN algoritması

ANOMALOUS ACTIVITY DETECTION FROM DAILY SOCIAL MEDIA USER MOBILITY DATA

Anomalous activities are the activities that do not fit into normal and routine behavior of people or objects. Anomalous activity, account, or sharing detection from social networks play an important role for preventing social media users from harmful and annoying contents. However, detecting anomalous activities is challenging due to the difficulty of separating anomalous activities from real ones, limitations of current algorithms and interest measures, the challenge of analyzing social media big data, and hardness of handling spatial and temporal dimensions. In this study, anomalous activities are detected using daily social media user mobility data. In particular, two features are extracted from daily social media user mobility, namely, daily total number of visited locations and daily total distance, and these features are used for detecting anomalous activities. An algorithm, that employs DBSCAN clustering algorithm, is proposed for detecting such activities. The results show that proposed algorithm could learn normal daily activities of social media users and detect anomalous activities.

Keywords:

anomalous activity detection, social networks, spatial social media mining, DBSCAN algorithm,

PDF

___

[1] JIN, L., CHEN, Y., WANG, T., HUI, P.,VASILAKOS, A. V., "Understanding user behavior in online social networks: a survey", IEEE Communications Magazine, 51: 144-150, 2013.
[2] YU, R., QIU, H., WEN, Z., LIN, C.,LIU, Y., "A Survey on Social Media Anomaly Detection", SIGKDD Explor. Newsl., 18: 1-14, 2016.
[3] ZAFARANI, R., ABBASI, M. A., LIU, H., " Social Media Mining: An Introduction", Cambridge University Press, p. 332, 2014.
[4] PENG, H., BAO, M., LI, J., BHUIYAN, M. Z. A., LIU, Y., HE, Y., YANG, E., "Incremental Term Representation Learning for Social Network Analysis", Future Generation Computer Systems, 86: 1503-1512, 2018.
[5] ECEMIŞ, A., DOKUZ, A. Ş., ÇELIK, M., "Sentiment Analysis of Posts of Social Media Users in Their Socially Important Locations", 2018 International Conference on Artificial Intelligence and Data Processing (IDAP), 2015, pp. 1-6.
[6] RONG, H., MA, T., TANG, M., CAO, J., "A novel subgraph K+-isomorphism method in social network based on graph similarity detection", Soft Computing, 22(8): 2583-2601, 2018.
[7] LEI, K., LIU, Y., ZHONG, S., LIU, Y., XU, K., SHEN, Y., YANG, M., "Understanding User Behavior in Sina Weibo Online Social Network: A Community Approach", IEEE Access, 6: 13302-13316, 2018.
[8] SCELLATO, S., NOULAS, A., LAMBIOTTE, R., MASCOLO, C., "Socio-spatial properties of online location-based social networks", Fifth International AAAI Conference on Weblogs and Social Media, 2011, pp. 329-336.
[9] DOKUZ, A. S.,CELIK, M., "Discovering socially important locations of social media users", Expert Systems with Applications, 86: 113-124, 2017.
[10] CELIK, M.,DOKUZ, A. S., "Discovering socio-spatio-temporal important locations of social media users", Journal of Computational Science, 22: 85-98, 2017.
[11] SAVAGE, D., ZHANG, X., YU, X., CHOU, P.,WANG, Q., "Anomaly detection in online social networks", Social Networks, 39: 62-70, 2014.
[12] CHEN, C.-M., GUAN, D. J.,SU, Q.-K., "Feature set identification for detecting suspicious URLs using Bayesian classification in social networks", Information Sciences, 289: 133-147, 2014.
[13] TAKAHASHI, T., TOMIOKA, R.,YAMANISHI, K., "Discovering Emerging Topics in Social Streams via Link-Anomaly Detection", IEEE Transactions on Knowledge and Data Engineering, 26: 120-130, 2014.
[14] TRÅNG, D., JOHANSSON, F.,ROSELL, M., Evaluating Algorithms for Detection of Compromised Social Media User Accounts. Proc. 2015 Second European Network Intelligence Conference, 2015,pp. 75-82
[15] RUAN, X., WU, Z., WANG, H.,JAJODIA, S., "Profiling Online Social Behaviors for Compromised Account Detection", IEEE Transactions on Information Forensics and Security, 11: 176-187, 2016.
[16] SONG, J., LEE, S.,KIM, J., "CrowdTarget: Target-based Detection of Crowdturfing in Online Social Networks", Proceedings of the 22nd ACM SIGSAC Conference on Computer and Communications Security, 793-804, Denver, Colorado, USA, 2015.
[17] ASWANI, R., GHRERA, S. P., KAR, A. K.,CHANDRA, S., "Identifying buzz in social media: a hybrid approach using artificial bee colony and k-nearest neighbors for outlier detection", Social Network Analysis and Mining, 7: 38, 2017.
[18] GURAJALA, S., WHITE, J. S., HUDSON, B., VOTER, B. R.,MATTHEWS, J. N., "Profile characteristics of fake Twitter accounts", Big Data & Society, 3: 2053951716674236, 2016.
[19] GILANI, Z., KOCHMAR, E.,CROWCROFT, J., "Classification of Twitter Accounts into Automated Agents and Human Users", Proceedings of the 2017 IEEE/ACM International Conference on Advances in Social Networks Analysis and Mining 2017, 489-496, Sydney, Australia, 2017.
[20] WALT, E. V. D.,ELOFF, J., "Using Machine Learning to Detect Fake Identities: Bots vs Humans", IEEE Access, 6: 6540-6549, 2018.
[21] YU, R., HE, X.,LIU, Y., "GLAD: Group Anomaly Detection in Social Media Analysis", ACM Trans. Knowl. Discov. Data, 10: 1-22, 2015.
[22] KAUR, R., KAUR, M.,SINGH, S., "A Novel Graph Centrality Based Approach to Analyze Anomalous Nodes with Negative Behavior", Procedia Computer Science, 78: 556-562, 2016.
[23] LIAO, Q., SHI, L.,WANG, C., "Visual analysis of large-scale network anomalies", IBM Journal of Research and Development, 57: 13:11-13:12, 2013.
[24] JEONG, S., NOH, G., OH, H.,KIM, C.-K., "Follow spam detection based on cascaded social information", Information Sciences, 369: 481-499, 2016.
[25] FENG, B., LI, Q., PAN, X., ZHANG, J.,GUO, D., "GroupFound: An effective approach to detect suspicious accounts in online social networks", International Journal of Distributed Sensor Networks, 13: 1550147717722499, 2017.
[26] DUTTA, H. S., CHETAN, A., JOSHI, B.,CHAKRABORTY, T., Retweet Us, We will Retweet You: Spotting Collusive Retweeters Involved in Blackmarket Services. Proc. 2018 IEEE/ACM International Conference on Advances in Social Networks Analysis and Mining (ASONAM), 2018,pp. 242-249
[27] ESWARAN, D., FALOUTSOS, C., GUHA, S.,MISHRA, N., "SpotLight: Detecting Anomalies in Streaming Graphs", Proceedings of the 24th ACM SIGKDD International Conference on Knowledge Discovery & Data Mining, 1378-1386, London, United Kingdom, 2018.
[28] GABRIELLI, L., RINZIVILLO, S., RONZANO, F.,VILLATORO, D., From Tweets to Semantic Trajectories: Mining Anomalous Urban Mobility Patterns. Proc. International Workshop on Citizen in Sensor Networks, 2013,pp. 26-35
[29] ZHENG, Y., ZHANG, H.,YU, Y., "Detecting collective anomalies from multiple spatio-temporal datasets across different domains", Proceedings of the 23rd SIGSPATIAL International Conference on Advances in Geographic Information Systems, 1-10, Seattle, Washington, 2015.
[30] CHAE, J., CUI, Y., JANG, Y., WANG, G., MALIK, A.,EBERT, D. S., Trajectory-based visual analytics for anomalous human movement analysis using social media. Proc. EuroVis Workshop on Visual Analytics (EuroVA), 2015,pp. 1-5
[31] PAN, B., ZHENG, Y., WILKIE, D.,SHAHABI, C., "Crowd sensing of traffic anomalies based on human mobility and social media", Proceedings of the 21st ACM SIGSPATIAL International Conference on Advances in Geographic Information Systems, 344-353, Orlando, Florida, 2013.
[32] JAYARAJAH, K., SUBBARAJU, V., WEERAKOON, D., MISRA, A., TAM, L. T.,ATHAIDE, N., Discovering anomalous events from urban informatics data. Proc. Ground/Air Multisensor Interoperability, Integration, and Networking for Persistent ISR VIII, 2017 10190,pp. 101900F
[33] GIRIDHAR, P., AMIN, M. T., ABDELZAHER, T., WANG, D., KAPLAN, L., GEORGE, J.,GANTI, R., "ClariSense+: An enhanced traffic anomaly explanation service using social network feeds", Pervasive and Mobile Computing, 33: 140-155, 2016.
[34] HUANG, C., WU, X.,WANG, D., "Crowdsourcing-based Urban Anomaly Prediction System for Smart Cities", Proceedings of the 25th ACM International on Conference on Information and Knowledge Management, 1969-1972, Indianapolis, Indiana, USA, 2016.
[35] WU, X., DONG, Y., HUANG, C., XU, J., WANG, D.,CHAWLA, N. V., UAPD: Predicting Urban Anomalies from Spatial-Temporal Data. Proc. Joint European Conference on Machine Learning and Knowledge Discovery in Databases, 2017,pp. 622-638
[36] SOUZA, R. C. S. N. P., ASSUNÇÃO, R. M., OLIVEIRA, D. M., NEILL, D. B.,MEIRA, W., "Where did I get dengue? Detecting spatial clusters of infection risk with social network data", Spatial and Spatio-temporal Epidemiology2018.
[37] ESTER, M., KRIEGEL, H.-P., #246, SANDER, R.,XU, X., "A density-based algorithm for discovering clusters a density-based algorithm for discovering clusters in large spatial databases with noise", Proceedings of the Second International Conference on Knowledge Discovery and Data Mining, 226-231, Portland, Oregon, 1996.
[38] OZKOK, F. O.,CELIK, M., "A New Approach to Determine Eps Parameter of DBSCAN Algorithm", 2017, 5: 5, 2017.
[39] ÇELIK, M., DADAŞER-ÇELIK, F.,DOKUZ, A. Ş., Anomaly detection in temperature data using DBSCAN algorithm. Proc. 2011 International Symposium on Innovations in Intelligent Systems and Applications, 2011,pp. 91-95
[40] DEY, R.,CHAKRABORTY, S., Convex-hull & DBSCAN clustering to predict future weather. Proc. 2015 International Conference and Workshop on Computing and Communication (IEMCON), 2015,pp. 1-8
[41] EDLA, D. R.,JANA, P. K., "A Prototype-Based Modified DBSCAN for Gene Clustering", Procedia Technology, 6: 485-492, 2012.
[42] DOKUZ, A. S., DEMOLLI, H., GOKCEK, M.,ECEMIS, A., "Year-Ahead Wind Speed Forecasting using a Clustering-Statistical Hybrid Method", CIEA’ 2018 International Conference on Innovative Engineering Applications, 971-975, Sivas, Turkey, 2018.
[43] LIU, J., HAO, F.,WANG, Y., Discovering Influential Areas According to Check-In Records and User Influence in Social Networks. Proc. 2018 IEEE 20th International Conference on High Performance Computing and Communications; IEEE 16th International Conference on Smart City; IEEE 4th International Conference on Data Science and Systems (HPCC/SmartCity/DSS), 2018,pp. 1151-1155
[44] REZAEI, M.: ‘Clustering validation’, University of Eastern Finland, 2016
[45] https://developer.twitter.com/en/docs, (erişim tarihi 04.03.2019)
[46] http://twitter4j.org/en/index.html, (erişim tarihi 04.03.2019)
[47] BENEVENUTO, F., MAGNO, G., RODRIGUES, T.,ALMEIDA, V., "Detecting Spammers on Twitter", CEAS 2010 - Seventh annual Collaboration, Electronic messaging, AntiAbuse and Spam Conference, 1-9, Redmond, Washington, USA, 2010.
[48] ZHENG, X., ZENG, Z., CHEN, Z., YU, Y.,RONG, C., "Detecting spammers on social networks", Neurocomputing, 159: 27-34, 2015.