AIRCC's International Journal of Computer Science and Information Technology

Open Access Open Access  Restricted Access Subscription Access

Discovering Users Topic of Interest from Tweet


Affiliations
1 Department of Computer Science and Engineering, CUET, Chittagong, Bangladesh
2 Department of Business Administration, IIUC, Chittagong, Bangladesh
3 Department of Computer Science and Engineering, CIU, Chittagong, Bangladesh
 

Nowadays social media has become one of the largest gatherings of people in online. There are many ways for the industries to promote their products to the public through advertising. The variety of advertisement is increasing dramatically. Businessmen are so much dependent on the advertisement that significantly it really brought out success in the market and hence practiced by major industries. Thus, companies are trying hard to draw the attention of customers on social networks through online advertisement. One of the most popular social media is Twitter which is popular for short text sharing named ‘Tweet'. People here create their profile with basic information. To ensure the advertisements are shown to relative people, Twitter targets people based on language, gender, interest, follower, device, behaviour, tailored audiences, keyword, and geography targeting. Twitter generates interest sets based on their activities on Twitter. What our framework does is that it determines the topic of interest from a given list of Tweets if it has any. This process is called Entity Intersect Categorizing Value (EICV). Each category topic generates a set of words or phrases related to that topic. An entity set is created from processing tweets by keyword generation and Twitters data using Twitter API. Value of entities is matched with the set of categories. If they cross a threshold value, it results in the category which matched the desired interest category. For smaller amounts of data sizes, the results show that our framework performs with higher accuracy rate.

Keywords

Tweet Analyse, Topic Generation, Social Media Interest Generator, Topic of Tweet, Short Text Analyse, Predict Topic from Tweet.
User
Notifications
Font Size

  • J. A. Obar and S. S. Wildman, (2015) “Social media definition and the governance challenge: An introduction to the special issue”, Telecommunications Policy, vol. 39(9), pp. 745-750. DOI:http://dx.doi.org/10.2139/ssrn.2647377

  • S. Goyal, (2013) “Advertising on social media”, Scientific Journal of Pure and Applied Sciences, vol.2, no. 5, pp. 220–223.

  • M. L. Chan, H. L. Chee, S. P. Chin, and G. X. Sim, (2014)“Consumers' attitude towards online advertising: the study on information responses”, BIB (Hons.) thesis, UTAR. http://eprints.utar.edu.my/id/eprint/1348

  • X. Y. Leung, B. Bai, and K. A. Stahura, (2015) “The marketing effectiveness of social media in the hotel industry: A comparison of Facebook and Twitter", Journal of Hospitality & Tourism Research, vol. 39, no. 2, pp. 147-169. DOI: https://doi.org/10.1177/1096348012471381

  • G. Bakshi, and S. K. Gupta, (2013) “Online advertising and its impact on consumer buying behavior", International Journal of Research in Finance and Marketing, vol. 3, no. 1, pp. 21-30.

  • B. Pikas, and G. Sorrentino, (2014) “The effectiveness of online advertising: consumers perceptions of ads on Facebook, Twitter and Youtube", Journal of Applied Business and Economics, vol. 16, no.

  • , p. 70-81.

  • K. Ho, V. Liesaputra, S. Yongchareon, and M. Mohaghegh,(2017) “A framework for evaluating anti spammer systems for Twitter", In Panetto H. et al. (eds): OTM Conferences On the Move to Meaningful Internet Systems. Lecture Notes in Computer Science, vol. 10573, Springer, pp. 648-662. DOI: https://doi.org/10.1007/978-3-319-69462-7_41

  • M. E. Waring, K. L. Schneider, B. M. Appelhans, T. A.M. Simas, R. S. Xiao, M. C. Whited, A. M.

  • Busch, M. M.Evans, and S. L. Pagoto, (2016) “Interest in a Twitter-delivered weight loss program among women of childbearing age", Translational Behavioral Medicine, vol. 6, no. 2, Springer, pp. 277-284. DOI:10.1007/s13142-015-0382-4

  • T. Uchiya, Y. Ishida, Y. Kume, and I. Takumi, (2016) “Proposal of follow user recommendation system on Twitter based on interest domain", In IEEE 5th Global Conference on Consumer Electronics. DOI: 10.1109/GCCE.2016.7800413

  • D. Liu and H. R.Weistroffer, (2016) “A look at online targeted advertising in information systems research”, In Proceedings of the Southern Association for Information Systems Conference (SAIS), USA. https://aisel.aisnet.org/sais2016/17

  • X. He, J. Pan, O. Jin, T. Xu, B. Liu, T. Xu, Y. Shi, A. Atallah, R. Herbrich,S. Bowers, et al., (2014) “Practical lessons from predicting clicks on ads at Facebook”, In Proceedings of the Eighth International Workshop on Data Mining for Online Advertising, ACM, pp. 1–9. DOI: 10.1145/2648584.2648589

  • D. E. McCorkle and J. M. Payan, (2017) “Using Twitter in the marketing and advertising classroom to develop skills for social media marketing and personal branding”, Journal of Advertising Education, vol.21(1), pp. 33-43.


Abstract Views: 279

PDF Views: 138




  • Discovering Users Topic of Interest from Tweet

Abstract Views: 279  |  PDF Views: 138

Authors

Muhammad Kamal Hossen
Department of Computer Science and Engineering, CUET, Chittagong, Bangladesh
Md. Ali Faiad
Department of Computer Science and Engineering, CUET, Chittagong, Bangladesh
Md. Shahnur Azad Chowdhury
Department of Business Administration, IIUC, Chittagong, Bangladesh
Md. Sajjatul Islam
Department of Computer Science and Engineering, CIU, Chittagong, Bangladesh

Abstract


Nowadays social media has become one of the largest gatherings of people in online. There are many ways for the industries to promote their products to the public through advertising. The variety of advertisement is increasing dramatically. Businessmen are so much dependent on the advertisement that significantly it really brought out success in the market and hence practiced by major industries. Thus, companies are trying hard to draw the attention of customers on social networks through online advertisement. One of the most popular social media is Twitter which is popular for short text sharing named ‘Tweet'. People here create their profile with basic information. To ensure the advertisements are shown to relative people, Twitter targets people based on language, gender, interest, follower, device, behaviour, tailored audiences, keyword, and geography targeting. Twitter generates interest sets based on their activities on Twitter. What our framework does is that it determines the topic of interest from a given list of Tweets if it has any. This process is called Entity Intersect Categorizing Value (EICV). Each category topic generates a set of words or phrases related to that topic. An entity set is created from processing tweets by keyword generation and Twitters data using Twitter API. Value of entities is matched with the set of categories. If they cross a threshold value, it results in the category which matched the desired interest category. For smaller amounts of data sizes, the results show that our framework performs with higher accuracy rate.

Keywords


Tweet Analyse, Topic Generation, Social Media Interest Generator, Topic of Tweet, Short Text Analyse, Predict Topic from Tweet.

References