Turkish Journal of Computer and Mathematics Education
Vol.12 No.9 (2021), 434 - 437
434
Research Article
The Probability of Microblog Forwarding using Multi-Message Interaction-Driving
Mechanism
Dr B V Subba Rao1, Mr. Raja Kondaveeti2, Mr.Y.Ramu3, Dr V. Shanmukha Rao4, Dr G.Siva Nageswara
Rao5
1 Professor, Dept of IT, PVP Siddhartha Institute of Technology, Vijayawada, A.P
2Associate Professor, Dept of IT, Swarnandra College of Engineering and Technology, Narasapurm, A.P 3Associate Professor, Dept of CSE, Shri Vishnu Engineering College for Women, Bimavaram, A.P 4Professor, Dept of IT, Andhra Loyola College of Engineering and Technology, Vijayawada, A.P
5Professor, Department of CSE, Koneru Lakshmaiah Education Foundation, Vaddeswara, Guntur(dt), AP, India 1 Corresponding author e-mail:bvsrau@gmail.com
Article History: Received: 10 January 2021; Revised: 12 February 2021; Accepted: 27 March 2021; Published
online: 20 April 2021
ABSTRACT: Social media plays the major role in analyzing the user behavior based on the multiple messages given by the
users by using social platform. From recent days every user is participating in social media for messaging the hot social topics. These are of two ways, one it considers the multi-message interaction on behavior of the users that participates to analyzes of multi-message interaction that influence the user behavior that shows more accurately. The second stage, using the back-propagation (BP) neural networks the users are managed in multi-message hotspots. In this paper, a new user prediction model is developed for the social hotspots based on a multi-message interaction-driving mechanism (MIDM) which integrates the BP neural network. The performance is calculated based on the improved accuracy.
KEYWORDS: Social hotspots, User behavior, BP neural network.
1. INTRODUCTION:
Individuals' communication and way of life have achieved huge changes. The age and spread of hotly debated issues in online media are continually influencing the day by day lives of individuals. The social areas of interest allude to news or themes that are concerned or intrigued by general society as of now. The interpersonal organization geography and the client's peruses and answers to messages in the organization advance the scattering and development of data identified with the intriguing issue, that is, the proliferation of the organization subjects [1]. Thusly, dominating client sending cooperation conduct is significant for assessing the impact of a microblog theme, checking popular assessment through organizations [3], [4], and data recovery.
As of now, the expectation of client conduct in interpersonal organizations essentially incorporates the accompanying two methodologies. The principal approach investigates the primary geography map utilized for data dispersal in informal communities. This methodology predicts the way and scope of the data engendering and, thus, the client's cooperation conduct. Which clients will partake in the microblog is regularly anticipated by powerful engendering or an irresistible illness model. Such prescient models ordinarily group network hubs as questions, communicators, and immunizers.
2. LITERATURE SURVEY: 2.1 M. Salehi, R. Sharma, ; et al
A few systems are introduced as a set of associated organizations or organizations with numerous sorts of associations, here by and large called multilayer networks. Spreading cycles, for example, data proliferation among clients of online informal organizations, or the dissemination of microbes among people through their contact organization, are principal wonders happening in these organizations. However, while data dissemination in single organizations has gotten impressive consideration from different orders for longer than 10 years,
Turkish Journal of Computer and Mathematics Education
Vol.12 No.9 (2021), 434 - 437
435
Research Article
spreading measures in multilayer networks is as yet a recent area of research that introduces many testing research issues.
2.2 J. Golbeck, C. Robles et al
This process is very interested in analyzing the personality of users. The behaviour of the user is estimated by using various types of messages that are analyzed within the twitter. The proposed method in this system is Soft Frequent Pattern Mining (SFPM) algorithm which is used to analyze the huge size that is based on the tweets and time. From the user's point of view, various types of keywords are used to request the twitter which is significantly used to extract the new similar words that reflects the topic based on the main topic.
3. PROBLEM DEFINTION:
The author [5] proposed a new model which is called as two-level model that finds and checks the impact of users by thinking about the interaction between users. The author [6] developed the method which is topological guide that considers the data dispersal by using an interpersonal organization. The author [7] removes the advantages of the multilayer network structure for foreseeing the similar microblog using. Different specialists [8], [9] anticipated client sending conduct through related ascribes utilizing an AI strategy. Grabowicz et al. [10] anticipated the client sending conduct by sifting the variables that are unequivocally identified with client practices.
4. PROPOSED APPROACH:
The proposed system is mainly focuses on analyses of various social media messages that are given by the users. This model BP neural network model adopts the deep learning algorithms and gets accurate results. In the interim, because of the iterative direction of the multi-information association on client conduct, the BP neural organization was debased by the over-fitting issue.
Subsequent to rectifying the over-fitting by a recreated strengthening calculation, the exactness of the expectation was improved. At last, we characterized the various message relationship measurements, genuinely broke down the model yields, and assessed the extent of clients taking an interest in one message, who likewise took part in different messages.
5. NETWORK ARCHITECTURE:
The following figure 1 shows the network architecture. It depicts the details of input data submitted and the model applied with active message participation and as well non participation. Based on the input and the proposed approach a systematic output is achieved.
Turkish Journal of Computer and Mathematics Education
Vol.12 No.9 (2021), 434 - 437
436
Research Article
Figure 1: System architecture 6. PROPOSED METHODOLOGY:
6.1 INFLUENCE QUANTIFICATION:
Many users in social networking sites participating in the messaging of interesting issues for assorted reasons. The objects are generally isolated into two classes: the client's own advantage and multi-message communication. To measure the impacts of various variables on cooperation conduct, we need the impact property of the client's support conduct, which relies upon both the client's very own advantage attributes and the impacts of multi-message associations.
6.2 FORWARDING PREDICTION:
The data pre-processing is done and it is calculated by the different components that are based on multi-message communication with the client. This system gives the prediction of the every message given by the user weather it is good or not. Based on the user interest the analysation is done with different topic.
6.3 ALGORITHM COMPLEXITY:
The basic data is represented as N = {(n j, mi)|mi ∈ M} of the numerous messages in the famous discussion, the multi-message interaction-driving mechanism is extracted from the multiple messages M = {m1, m2,..., mn} and the user participation network Gmi U = (U, mi) under the most improved topic. The new user’s proposed method is adopted from the historical behaviors data A = {(ai, bi, ωi,t)|t ∈ ψ, ωi ∈ U} and tags L = {(ci, ωi)|ωi ∈ U} of the participants.
7. RESULTS:
The results of our proposed approach are shown the following figures 2 and 3. This result shows the tweet score as well its behaviors detection. Based on the tweets and its behavior we can believe that our proposed model is most optimal compared with other existing methods.
Turkish Journal of Computer and Mathematics Education
Vol.12 No.9 (2021), 434 - 437
437
Research Article
Figure 3: Behavior Detection 8. CONCLUSION:
The proposed strategy was tentatively assessed on multi-message information under a hotly debated issue examined on the online interpersonal organization, Sina Weibo. The model precisely anticipated the client's support practices as well as measured the force of the shared impact between the numerous messages. Besides, it progressively saw the situational changes in the interesting issue, offering solid help for general assessment control.
9. REFERENCES:
[1] M. Takayasu, K. Sato, Y. Sano, K. Yamada, W. Miura, and H. Takayasu, “Rumor diffusion and convergence during the 3.11 earthquake: A Twitter case study,” PLoS ONE, vol. 10, no. 4, Apr. 2015, Art. no. e0121443. [2] Y. Du, Y. He, Y. Tian, Q. Chen, and L. Lin, “Microblog bursty topic detection based on user relationship,” in Proc. 6th IEEE Joint Int. Inf. Technol. Artif. Intell. Conf., vol. 1, Aug. 2011, pp. 260–263.
[3] S. Gaglio, G. Lo Re, and M. Morana, “A framework for real-time Twitter data analysis,” Comput. Commun., vol. 73, pp. 236–242, Jan. 2016.
[4] G. Verma, A. Swami, and K. Chan, “The impact of competing zealots on opinion dynamics,” Phys. A, Stat. Mech. Appl., vol. 395, pp. 310–331, Feb. 2014.
[5] L.-L. Ma, C. Ma, H.-F. Zhang, and B.-H. Wang, “Identifying influential spreaders in complex networks based on gravity formula,” Phys. A, Stat. Mech. Appl., vol. 451, pp. 205–212, Jun. 2016.
[6] A. Mislove, M. Marcon, K. P. Gummadi, P. Druschel, and B. Bhattacharjee, “Measurement and analysis of online social networks,” in Proc. 7th ACM SIGCOMM Conf. Internet Meas., 2007, pp. 29–42.
[7] X. Yun-Peng, L. Song-Yang, and L. Yan-Bing, “An information diffusion dynamic model based on social influence and mean-field theory,” Acta Phys. Sinica, vol. 66, no. 3, 2017.
[8] Q. Su, J. Huang, and X. Zhao, “An information propagation model considering incomplete reading behavior in microblog,” Phys. A, Stat. Mech. Appl., vol. 419, pp. 55–63, Feb. 2015.
[9] L.-L. Xia, G.-P. Jiang, B. Song, and Y.-R. Song, “Rumor spreading model considering hesitating mechanism in complex social networks,” Phys. A, Stat. Mech. Appl., vol. 437, pp. 295–303, Nov. 2015.
[10] R. Jie, J. Qiao, G. Xu, and Y. Meng, “A study on the interaction between two rumors in homogeneous complex networks under symmetric conditions,” Phys. A, Stat. Mech. Appl., vol. 454, pp. 129–142, Jul. 2016.
