%0 Journal Article %1 hossendiscovering %A Hossen, Muhammad Kamal %A Faiad, Md. Ali %A Chowdhury, Md. Shahnur Azad %A Islam, Md. Sajjatul %D 2018 %J International Journal of Computer Science & Information Technology (IJCSIT) %K Tweet analyse from generation generator interest media of predict short social text topic twee tweet %N 1 %P 95 - 105 %R 10.5121/ijcsit.2018.10108 %T Discovering Users Topic of Interest from Tweet %U http://airccse.org/journal/ijcsit2018_curr.html %V 10 %X 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.

@article{hossendiscovering, 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.}, added-at = {2020-08-18T11:44:01.000+0200}, author = {Hossen, Muhammad Kamal and Faiad, Md. Ali and Chowdhury, Md. Shahnur Azad and Islam, Md. Sajjatul}, biburl = {https://www.bibsonomy.org/bibtex/263d90f82e61b3844e88a904af45e5452/shamerjose}, doi = {10.5121/ijcsit.2018.10108}, interhash = {bfea115f2486f0085c881144dc996704}, intrahash = {63d90f82e61b3844e88a904af45e5452}, journal = {International Journal of Computer Science & Information Technology (IJCSIT) }, keywords = {Tweet analyse from generation generator interest media of predict short social text topic twee tweet}, month = feb, number = 1, pages = {95 - 105}, timestamp = {2020-08-18T11:44:01.000+0200}, title = {Discovering Users Topic of Interest from Tweet}, url = {http://airccse.org/journal/ijcsit2018_curr.html}, volume = 10, year = 2018 }