انتخاب ويژگي براي شناسايي نويسنده در متون کوتاه برخط فارسي
محورهای موضوعی :سمیه عارفی 1 , محمد احسان بصیری 2 , امید روزمند 3
1 - دانشجو
2 - مربی
3 - مربی
کلید واژه: تحليل متن, تحليل سبک, استخراج ويژگي, انتخاب ويژگي و شناسايي نويسنده. ,
چکیده مقاله :
رشد فزايندهي استفاده از رسانه‌هاي اجتماعي و ارتباطات برخط به‌منظور بيان نظرات، تبادل عقايد و همچنين گسترش استفادهي کاربران فارسي زبان از اين ابزارها باعث افزايش متون فارسي در وب شده است. اين رشد چشمگير در کنار سوءاستفادههاي ناشي از ناشناس بودن نويسندهي نوشتهها نياز به سامانهي خودکار شناسايي نويسنده در اين زبان را بيش از پيش آشکار مي‌سازد. هدف از اين پژوهش، بررسي ويژگي‌هاي مؤثر در شناسايي نويسندگان نظرات فارسي توليد شده توسط خريداران گوشي و همچنین ارزیابی روش‌های نظارتی و غیرنظارتی می‌باشد. عواملي که در اين پژوهش بررسي ميشود شامل ويژگي‌هاي لغوي، نگارشی، معنايي، ساختاري، دستوري، مختص متن و مختص شبکه‌هاي اجتماعي است. پس از استخراج ويژگي‌هاي مذکور، انتخاب ويژگي‌هاي برتر توسط چهار الگوريتم همبستگي ويژگي، نسبت بهره، OneR و تحليل اجزاي اصلي آزمايش ميشود. در ادامه از الگوريتم‌هاي K-means، EM و خوشه‌بندي مبتني بر چگالي براي خوشه‌بندي و الگوريتم‌هاي شبکهي بيز، جنگل تصادفي و Bagging براي دستهبندي استفاده خواهد شد. ارزيابي الگوريتم‌هاي فوق بر روي نظرات فارسي مربوط به خريداران گوشي‌هاي سامسونگ نشان ميدهد که بهترين تشخيص در بين الگوريتم‌هاي خوشه‌بندي با دقت 16/59% مربوط به الگوريتم EM روي 15 ويژگي برتر انتخابي توسطOneR است درحالي‌که الگوريتم جنگل تصادفي به‌همراه نسبت بهره برای 90 ویژگی با دقت 57/79% بهترين کارايي را در بين الگوريتم‌هاي دستهبندي دارد. همچنين مقايسه‌ی ويژگي‌ها نشان داد که ويژگي‌هاي نگارشی بيشترين تأثير را در شناسايي نويسندهي متون کوتاه داشته و پس از آن به‌ترتيب ويژگي‌هاي لغوي ، مختص متن، مختص شبکه‌های اجتماعی، ساختاري، دستوري و معنایی قرار گرفتند.
The growing use of social media and online communication to express opinions, exchange ideas, and also the expanding use of of this platforms by Persian users has increased Persian texts on the Web. This remarkable growth, along with abusive use of the writer's anonymity, reveals the need for the author's automatic identification system in this language. In this research, the purpose of the study is to investigate the factors affecting the identification of authors of Persian reviews produced by cell-phone buyers and also to evaluate supervised and unsupervised methods. The factors considered in this research include lexical, syntactic, semantic, structural, grammatical, text-specific, and specific to social networks. After extracting these features, selecting the best features is tested by four algorithms including feature correlation, gain ratio, OneR, and principal components analysis. In the following, K-means, EM and density-based clustering will be used for clustering and Bayesian network, random forest, and Bagging will be used for categorization. The evaluation of the above algorithms on Persian comments of Samsung phone buyers indicates that the best performance among the clustering algorithms is 59/16% obtained by the EM algorithm on top-15 features selected by OneR, while the random forest algorithm using top-90 features selected by gain ratio with 79/57% achieves the best performance among the classification algorithms. Also, the comparison of features showed that syntactic features had the most effect on the identification of the author of short texts, and then, lexical, text-specific, specific to social networks, structural, grammatical and semantic features, respectively.
مرادي، مهدی و بحراني، محمد، “تشخيص خودکار جنسيت نويسنده در متون فارسي”، فصل‌نامه پردازش علائم و داده‌ها، شماره 4، پیاپی 26، صفحات 83-94، 1394.
[2] فرهمندپور، زینب، نیک‌مهر، هومان، منصوری زاده، محرم و طبیب زاده قمصری، اميد، “يک سيستم نوين هوشمند تشخيص هويت نويسنده فارسي زبان بر اساس سبک نوشتاري-مقاله برگزيده هفدهمين کنفرانس ملي انجمن کامپيوتر ايران”، مجله محاسبات نرم، شماره دوم، صفحات 35-26، 1391.
[3] F. Iqbal, H. Binsalleeh, B. C. M. Fung, and M. Debbabi, “Mining writeprints from anonymous e-mails for forensic investigation,” Digit. Investig., vol. 7, no. 1–2, pp. 56–64, 2010.
[4] S. Nirkhi, R. V Dharaskar, and V. M. Thakare, “Authorship Verification of Online Messages for Forensic Investigation,” Procedia Comput. Sci., vol. 78, pp. 640–645, 2016, doi: https://doi.org/10.1016/j.procs.2016.02.111.
[5] M. L. Brocardo, I. Traore, and I. Woungang, “Authorship verification of e-mail and tweet messages applied for continuous authentication,” J. Comput. Syst. Sci., vol. 81, no. 8, pp. 1429–1440, 2015.
[6] Y. Yiming and P. Jan O., “A Comparative Study on Feature Selection in Text Categorization,” Proceeding ICML ’97 Proc. Fourteenth Int. Conf. Mach. Learn., vol. 53, no. 9, pp. 412–420, 1997.
[7] M. Frederick and L. Wallace David, “Inference and Disputed Authorship: The Federalist. Reading, Addison.” Wessley Publishing Company. Republié sous le titre Applied Bayesian and …, 1984.
[8] T. C. Mendenhall, “The Characteristic Curves of Composition,” Science (80-. )., vol. 9, no. 214, pp. 237–249, Dec. 1887, [Online]. Available: http://www.jstor.org/stable/1764604.
[9] H. Craig, “Authorial attribution and computational stylistics: If you can tell authors apart, have you learned anything about them?,” Lit. Linguist. Comput., vol. 14, no. 1, pp. 103–113, 1999.
[10] M. Koppel and J. Schler, “Authorship verification as a one-class classification problem,” in Proceedings of the twenty-first international conference on Machine learning, 2004, p. 62.
[11] E. Villar-Rodriguez, J. Del Ser, M. N. Bilbao, and S. Salcedo-Sanz, “A feature selection method for author identification in interactive communications based on supervised learning and language typicality,” Eng. Appl. Artif. Intell., vol. 56, pp. 175–184, 2016, doi: https://doi.org/10.1016/j.engappai.2016.09.004.
[12] P. Geutner, U. Bodenhausen, and A. Waibel, “Flexibility through incremental learning: Neural networks for text categorization,” in Proceedings of WCNN-93, World Congress on Neural Networks, 1993, pp. 24–27.
[13] O. De Vel, “Mining e-mail authorship,” 2000.
[14] M. Corney, O. De Vel, A. Anderson, and G. Mohay, “Gender-preferential text mining of e-mail discourse,” in 18th Annual Computer Security Applications Conference, 2002. Proceedings., 2002, pp. 282–289.
[15] F. Iqbal, R. Hadjidj, B. C. M. Fung, and M. Debbabi, “A novel approach of mining write-prints for authorship attribution in e-mail forensics,” Digit. Investig., vol. 5, pp. S42–S51, 2008.
[16] A. Abbasi and H. Chen, “Writeprints: A stylometric approach to identity-level identification and similarity detection in cyberspace,” ACM Trans. Inf. Syst., vol. 26, no. 2, pp. 1–29, 2008.
[17] F. Iqbal, L. A. Khan, B. C. M. Fung, and M. Debbabi, “E-Mail Authorship Verification for Forensic Investigation,” in Proceedings of the 2010 ACM Symposium on Applied Computing, 2010, pp. 1591–1598, doi: 10.1145/1774088.1774428.
[18] B. Allison and L. Guthrie, “Authorship Attribution of E-Mail: Comparing Classifiers over a New Corpus for Evaluation.,” 2008.
[19] N. Cheng, R. Chandramouli, and K. P. Subbalakshmi, “Author gender identification from text,” Digit. Investig., vol. 8, no. 1, pp. 78–88, 2011.
[20] X. Chen, P. Hao, R. Chandramouli, and K. P. Subbalakshmi, “Authorship similarity detection from email messages,” in International Workshop on Machine Learning and Data Mining in Pattern Recognition, 2011, pp. 375–386.
[21] J. Keeshin, Z. Galant, and D. Kravitz, “Machine Learning and Feature Based Approaches to Gender Classification of Facebook Statuses.” 2010.
[22] R. Layton, P. Watters, and R. Dazeley, “Authorship Attribution for Twitter in 140 Characters or Less,” in 2010 Second Cybercrime and Trustworthy Computing Workshop, Jul. 2010, pp. 1–8, doi: 10.1109/CTC.2010.17.
[23] C. Li, A. Sun, and A. Datta, “Twevent: Segment-Based Event Detection from Tweets,” in Proceedings of the 21st ACM International Conference on Information and Knowledge Management, 2012, pp. 155–164, doi: 10.1145/2396761.2396785.
[24] J. S. Li, J. V Monaco, L.-C. Chen, and C. C. Tappert, “Authorship authentication using short messages from social networking sites,” in 2014 IEEE 11th International Conference on e-Business Engineering, 2014, pp. 314–319.
[25] A. Zubiaga, D. Spina, R. Martínez, and V. Fresno, “Real‐time classification of twitter trends,” J. Assoc. Inf. Sci. Technol., vol. 66, no. 3, pp. 462–473, 2015.
[26] A. Orebaugh, “An Instant Messaging Intrusion Detection System Framework: Using character frequency analysis for authorship identification and validation,” in Proceedings 40th Annual 2006 International Carnahan Conference on Security Technology, 2006, pp. 160–172.
[27] O. Canales et al., “A stylometry system for authenticating students taking online tests,” P. Student-Faculty Res. Day, Ed., CSIS. Pace Univ., 2011.
[28] C.-Y. Lai, “Author Gender Analysis’,” Final Proj. from I, vol. 256, 2009.
[29] H. Alam and A. Kumar, “Multi-lingual author identification and linguistic feature extraction—A machine learning approach,” in 2013 IEEE International Conference on Technologies for Homeland Security (HST), 2013, pp. 386–389.
[30] J. Adams, H. Williams, J. Carter, and G. Dozier, “Genetic Heuristic Development: Feature selection for author identification,” in 2013 IEEE Symposium on Computational Intelligence in Biometrics and Identity Management (CIBIM), 2013, pp. 36–41.
[31] J. Houvardas and E. Stamatatos, “N-gram feature selection for authorship identification,” in International conference on artificial intelligence: Methodology, systems, and applications, 2006, pp. 77–86.
[32] A. K. Uysal and S. Gunal, “A novel probabilistic feature selection method for text classification,” Knowledge-Based Syst., vol. 36, pp. 226–235, 2012, doi: https://doi.org/10.1016/j.knosys.2012.06.005.
[33] زنگويي، سمیرا، نعمتی شمس‌آباد، حسنعلی “شناسايي نويسندگان پيام هاي الکترونيکي از طريق واکاوي نوع و سبک نگارش آن ها مبتني بر روش هاي يادگيري ماشين(WKF based on SVM-PHGS) ”، پردازش و مديريت اطلاعات (علوم و فناوري اطلاعات)، شماره 2، دوره 29، صفحات 476-453، 1392.
[34] G. U. Yule, “The statistical study of literary vocabulary. Cambridge, Cambridge [Eng.].” University Press. Journal of the Royal Statistical Society, 1944.
[35] A. Honoré, “Some simple measures of richness of vocabulary,” Assoc. Lit. Linguist. Comput. Bull., vol. 7, no. 2, pp. 172–177, 1979.
[36] E. Brunet, Le Vocabulaire de Jean Giraudoux: structure et évolution : statistique et informatique appliquées à l’étude des textes à partir des données du Trésor de la langue française. Slatkine, 1978.
[37] H. S. Sichel, “On a Distribution Law for Word Frequencies,” J. Am. Stat. Assoc., vol. 70, no. 351a, pp. 542–547, 1975, doi: 10.1080/01621459.1975.10482469.
[38] E. H. SIMPSON, “Measurement of Diversity,” Nature, vol. 163, no. 4148, p. 688, 1949, doi: 10.1038/163688a0.
[39] S. Nemati, M. E. Basiri, N. Ghasem-Aghaee, and M. H. Aghdam, “A novel ACO–GA hybrid algorithm for feature selection in protein function prediction,” Expert Syst. Appl., vol. 36, no. 10, pp. 12086–12094, 2009, doi: https://doi.org/10.1016/j.eswa.2009.04.023.
