Comparative analysis on Facebook post interaction using DNN, ELM and LSTM

English version

Autoři: Sabih Ahmad Khan ^aff001; Hsien-Tsung Chang ^aff001
Působiště autorů: Department of Computer Science and Information Engineering, Chang Gung University, Taoyuan 33302, Taiwan ^aff001; Department of Physical Medicine and Rehabilitation, Chang Gung Memorial Hospital, Taoyuan 33302, Taiwan ^aff002
Vyšlo v časopise: PLoS ONE 14(11)
Kategorie: Research Article
prolekare.web.journal.doi_sk: https://doi.org/10.1371/journal.pone.0224452

Souhrn

This study presents a novel research approach to predict user interaction for social media post using machine learning algorithms. The posts are converted to vector form using word2vec and doc2vec model. These two methods are used to analyse the best approach for generating word embeddings. The generated word embeddings of post combined with other attributes like post published time, type of post and total interactions are used to train machine learning algorithms. Deep neural network (DNN), Extreme Learning Machine (ELM) and Long Short-Term Memory (LSTM) are used to compare the prediction of total interaction for a particular post. For word2vec, the word vectors are created using both continuous bag-of-words (CBOW) and skip-gram models. Also the pre-trained word vectors provided by google is used for the analysis. For doc2vec, the word embeddings are created using both the Distributed Memory model of Paragraph Vectors (PV-DM) and Distributed Bag of Words model of Paragraph Vectors (PV-DBOW). A word embedding is also created using PV-DBOW combined with skip-gram.

Klíčová slova:

Machine learning algorithms – Machine learning – Social media – Semantics – Preprocessing – Artificial neural networks – Word embedding – Facebook

Zdroje

1. Cvijikj IP, Spiegler ED, Michahelles F. The Effect of Post Type, Category and Posting Day on User Interaction Level on Facebook. In: 2011 IEEE Third International Conference on Privacy, Security, Risk and Trust and 2011 IEEE Third International Conference on Social Computing; 2011 Oct 9–11; Boston, MA; p. 810–813.

2. Aral S, Walker D. Creating Social Contagion Through Viral Product Design: A Randomized Trial of Peer Influence in Networks. Management Science. 2011 Aug 4; 57(9): 1623–1639. doi: 10.1287/mnsc.1110.1421

3. Myers SA, Zhu C, Leskovec J, Information diffusion and external influence in networks. In: Proc. 18th ACM SIGKDD Int. Conf. Knowl. Discovery Data Mining; 2012 Aug 12–16; p. 33–41.

4. Gomez-Rodriguez M, Leskovec J, Krause A. Inferring networks of diffusion and influence. In: Proc. 16th ACM SIGKDD Int. Conf. Knowl. Discovery Data Mining; 2010 Jul 25–28; p. 1019–1028.

5. Cha M, Haddadi H, Benevenuto F, Gummadi KP. Measuring user influence in Twitter: The million follower fallacy. In: Proc. 4th ICWSM; 2010 May 23–26; p. 10–17.

6. Bakshy E, Hofman JM, Mason WA, Watts DJ. Everyone’s an influencer: Quantifying influence on Twitter. In: Proc. WSDM; 2011 Feb 9–12; Hong Kong; p. 65–74.

7. Zhang J, Zhang R, Sun J, Zhang Y, Zhang C. TrueTop: A Sybil-resilient system for user influence measurement on Twitter. IEEE/ACM Trans. Netw. 2016 Oct; 24(5): 2834–2846. doi: 10.1109/TNET.2015.2494059

8. Statista (2017). Most famous social network sites worldwide as of September 2017, ranked by number of active users (in millions). Statista—The Statistics Portal. Retrieved: 2018 Jan 24, from https://www.statista.com/statistics/272014/global-social-networks-ranked-by-number-of-users/.

9. Statista (2017). Number of monthly active Facebook users worldwide as of 3rd quarter 2017 (in millions). Statista—The Statistics Portal. Retrieved: 2018 Jan 24, from https://www.statista.com/statistics/264810/number-of-monthly-active-facebook-users-worldwide/.

10. Ashley C, Tuten T. Creative Strategies in Social Media Marketing: An Exploratory Study of Branded Social Content and Consumer Engagement. Psychology Marketing. 2015; 32(1): 15–27. doi: 10.1002/mar.20761

11. Cvijikj IP, Michaheles F. A Case Study of the Effects of Moderator Posts within a Facebook Brand Page. In: Proc. 3rd Int. Conf. Social Informatics. 2011; Heidelberg, Berlin: Springer; 6984: 161–170.

12. Agnihotri R, Dingus R, Hu MY, Krush MT. Social media: Influencing customer satisfaction in B2B sales. Industrial Marketing Management. 2016; 53: 172–180. doi: 10.1016/j.indmarman.2015.09.003

13. Chang YT, Yu H, Lu HP. Persuasive messages, popularity cohesion, and message diffusion in social media marketing. Journal of Business Research. 2015 Apr; 68(4): 777–782. doi: 10.1016/j.jbusres.2014.11.027

14. Vries L, Gensler S, Leeflang PSH. Popularity of Brand Posts on Brand Fan Pages: An Investigation of the Effects of Social Media Marketing. Journal of Interactive Marketing. 2012 May; 26(2): 83–91. doi: 10.1016/j.intmar.2012.01.003

15. Zadeh AH, Sharda R. Modeling brand post popularity dynamics in online social networks. Decision Support Systems. 2014 Sep; 65: 59–68. doi: 10.1016/j.dss.2014.05.003

16. Lee JG, Moon S, Salamatian K. An Approach to Model and Predict the Popularity of Online Contents with Explanatory Factors. In: 2010 IEEE/WIC/ACM International Conference on Web Intelligence and Intelligent Agent Technology. 2010 Aug 31—Sep 3; Toronto, ON; p. 623–630.

17. Sabate F, Berbegal-Mirabent J, Cañabate A, Lebherz PR. Factors influencing popularity of branded content in Facebook fan pages. European Management Journal. 2014 Dec; 32(6): 1001–1011. doi: 10.1016/j.emj.2014.05.001

18. Liang PW, Dai BR. Opinion Mining on Social Media Data. In: 2013 IEEE 14th International Conference on Mobile Data Management. 2013 Jun 3–6; Milan, Italy; p. 91–96.

19. Bianchi C, Andrews L. Investigating marketing managers’ perspectives on social media in Chile. Journal of Business Research. 2015 Dec; 68(12): 2552–2559. doi: 10.1016/j.jbusres.2015.06.026

20. He W, Wu H, Yan G, Akula V, Shen J. A novel social media competitive analytics framework with sentiment benchmarks. Information and Management. 2015 Nov; 52(7): 801–812. doi: 10.1016/j.im.2015.04.006

21. Huang GB, Zhu QY, Siew CK. Extreme learning machine: Theory and applications. Neurocomputing. 2006 Dec; 70(1–3): 489–501. doi: 10.1016/j.neucom.2005.12.126

22. Hochreiter S, Schmidhuber J. Long Short-Term Memory. Neural Computation. 1997 Nov 15; 9(8): 1735–1780. doi: 10.1162/neco.1997.9.8.1735 9377276

23. Gers FA, Schmidhuber J, Cummins F. Learning to forget: Continual prediction with LSTM. Neural Computation. 2000 Oct; 12(10): 2451–2471. doi: 10.1162/089976600300015015 11032042

24. Mikolov T, Chen K, Corrado G, Dean J. Efficient estimation of word representations in vector space. arXiv:1301.3781. 2013. Available from: https://arxiv.org/abs/1301.3781.

25. Le Q, Mikolov T. Distributed representations of sentences and documents. In: Proc. ICML. 2014 Jun 22–24; Bejing, China; p. 1188–1196.

26. Mikolov T, Sutskever I, Chen K, Corrado G, Dean J. Distributed representations of words and phrases and their compositionality. In: Proc. Adv. Neural Inf. Process. Syst. 2013; p. 3111–3119.

27. Moro S, Rita P, Vala B. Predicting social media performance metrics and evaluation of the impact on brand building: A data mining approach. Journal of Business Research. 2016 Sep; 69(9): 3341–3351. doi: 10.1016/j.jbusres.2016.02.010

28. Straton N, Mukkamala RR, Vatrapu R. Big Social Data Analytics for Public Health: Predicting Facebook Post Performance Using Artificial Neural Networks and Deep Learning. In: 2017 IEEE International Congress on Big Data (BigData Congress). 2017 Jun 25–30; Honolulu, HI, USA; p. 89–96.

29. Straton N, Mukkamala RR, Vatrapu R. Big social data analytics for public health: Comparative methods study and performance indicators of health care content on Facebook. In: 2017 IEEE International Conference on Big Data (Big Data). 2017 Dec 11–14; Boston, MA, USA; p. 2772–2777.

30. Peng KH, Liou LH, Chang CS, Lee DS. Predicting personality traits of Chinese users based on Facebook wall posts. In: 2015 24th Wireless and Optical Communication Conference (WOCC). 2015 Oct 23–24; Taipei, Taiwan; p. 9–14.

31. Hinton G, Deng L, Yu D, Dahl G, Mohamed AR, Jaitly N, et al. Deep Neural Networks for Acoustic Modeling in Speech Recognition: The Shared Views of Four Research Groups. In: IEEE Signal Processing Magazine. 2012 Nov; 29(6): 82–97. doi: 10.1109/MSP.2012.2205597

32. Glorot X, Bordes A, Bengio Y. Deep Sparse Rectifier Neural Networks. In: Proceedings of the 14th International Conference on AISTATS. 2011; Fort Lauderdale, FL, USA; 15: 315–323.

33. Kingma DP, Ba J. Adam: A method for stochastic optimization. arXiv preprint arXiv:1412.6980. 2014. Available from: https://arxiv.org/abs/1412.6980.

34. Rong X. word2vec Parameter Learning Explained. arXiv:1411.2738. 2014. Available from: https://arxiv.org/abs/1411.2738.

35. Řehůřek R, Sojka P. Software Framework for Topic Modelling with Large Corpora. In: Proceedings of the LREC 2010 Workshop on New Challenges for NLP Frameworks. 2010 May; Valletta, Malta; p. 46–50.

36. Lau JH, Baldwin T. An Empirical Evaluation of doc2vec with Practical Insights into Document Embedding Generation. CoRR. arXiv:1607.05368. 2016. Available from: http://arxiv.org/abs/1607.05368.

37. Lee RJ, Sener IN, Mokhtarian PL, Handy SL. Relationships between the online and in–store shopping frequency of Davis, California residents. Transportation Research Part A: Policy and Practice. 2017 Jun; 100: 40–52.

38. Pappas IO, Kourouthanassis PE, Giannakos MN, Lekakos G. The interplay of online shopping motivations and experiential factors on personalized e-commerce: A complexity theory approach. Telematics and Informatics. 2017 Aug; 34(5): 730–742. doi: 10.1016/j.tele.2016.08.021

39. Pyle D. Data Preparation for Data Mining. San Francisco, CA: Morgan Kaufmann; 1999.

40. García S, Ramírez-Gallego S, Luengo J, Benítez JM, Herrera F. Big data preprocessing: methods and prospects. Big Data Analytics. 2016 Nov 1; 1(1): 1–22.

41. Sorzano COS, Vargas J, Montano AP. A survey of dimensionality reduction techniques. arXiv:1403.2877. 2014. Available from: https://arxiv.org/abs/1403.2877.

42. Khalid S, Khalil T, Nasreen S. A survey of feature selection and feature extraction techniques in machine learning. In: 2014 Science and Information Conference. 2014 Aug 27–29; London, UK; p. 372–378.

43. Schaidnagel M, Laux F, Connolly T. Using feature construction for dimensionality reduction in big data scenarios to allow real time classification of sequence data. Digital Enterprise Computing. Gesellschaft für Informatik e.V.; 2015. p. 259–269.

44. Chan C. Marketing the academic library with online social network advertising. Library Management. 2012 Oct 19; 33(8/9): 479–489. doi: 10.1108/01435121211279849

45. Leys C, Ley C, Klein O, Bernard P, Licata L. Detecting outliers: Do not use standard deviation around the mean, use absolute deviation around the median. Journal of Experimental Social Psychology. 2013 Jul; 49(4): 764–766. doi: 10.1016/j.jesp.2013.03.013

46. Pennington J, Socher R, Manning CD. GloVe: Global Vectors for Word Representation. In: Proc. Empirical Methods in Natural Language Processing (EMNLP). 2014 Oct 26–28; Doha, Qatar; p. 1532–1543.

47. Joulin A, Grave E, Bojanowski P, Mikolov T. Bag of Tricks for Efficient Text Classification. arXiv:1607.01759 [Preprint]. 2016. Available from: https://arxiv.org/abs/1607.01759.

48. Tang J, Deng C, Huang GB. Extreme Learning Machine for Multilayer Perceptron. IEEE Transactions on Neural Networks and Learning Systems. 2016 Apr; 27(4): 809–821. doi: 10.1109/TNNLS.2015.2424995 25966483

Comparative analysis on Facebook post interaction using DNN, ELM and LSTM

Souhrn

Klíčová slova:

Zdroje

PLOS One

Získaná hemofilie - Povědomí o nemoci a její diagnostika

Eozinofilní granulomatóza s polyangiitidou