Academia.eduAcademia.edu

Figure 5 – uploaded by Abu Foysal

See full PDFdownloadDownload figure
There are many different approaches towards detecting social automated bots. DeBot [22] is a per-user method with Pearson’s y2 method, which tests the independence of minutes-of-an-hour and seconds-of-a-minute. Limitation of this model is it cannot detect bot accounts with uniformly distributed activities. However, with the proposed model in this paper is using a totally different approach where by using sentiment analysis it is possible to ignore the problem with uniformly distributed activities.

Figure 5 There are many different approaches towards detecting social automated bots. DeBot [22] is a per-user method with Pearson’s y2 method, which tests the independence of minutes-of-an-hour and seconds-of-a-minute. Limitation of this model is it cannot detect bot accounts with uniformly distributed activities. However, with the proposed model in this paper is using a totally different approach where by using sentiment analysis it is possible to ignore the problem with uniformly distributed activities.

Related Figures (7)

Next, all the tweets are grouped by their twitter handle name and the following features for each twitter account is generated, as shown in Table 1 & Table 2. The user features extracted through the Twitter API are: @handle, total count, followers, following, retweet percentage, hashtags per tweet,
Next, all the tweets are grouped by their twitter handle name and the following features for each twitter account is generated, as shown in Table 1 & Table 2. The user features extracted through the Twitter API are: @handle, total count, followers, following, retweet percentage, hashtags per tweet,
Table 1: Feature extraction from the raw data of suspected Twitter bots. Table 2: Feature extraction from human user accounts.
Table 1: Feature extraction from the raw data of suspected Twitter bots. Table 2: Feature extraction from human user accounts.
Figure 2: Relationship between retrieved data and total set of data. International Journal of Computer Applications (0975 — 8887) Volume 177 — No. 25, December 2019
Figure 2: Relationship between retrieved data and total set of data. International Journal of Computer Applications (0975 — 8887) Volume 177 — No. 25, December 2019
the accounts were closed Figure 4: Botometer Classification Results able 3: Comparison between Botometer and SVM Classifier. down so it could not be used in the comparison with full effect. The final result shows, this paper’s classifier has less false positive in compared to Botometer® by OSoMe. Botometer has five false positive out of eight, whereas, SVM classifier has only two.
the accounts were closed Figure 4: Botometer Classification Results able 3: Comparison between Botometer and SVM Classifier. down so it could not be used in the comparison with full effect. The final result shows, this paper’s classifier has less false positive in compared to Botometer® by OSoMe. Botometer has five false positive out of eight, whereas, SVM classifier has only two.
580 California St., Suite 400
San Francisco, CA, 94104
© 2025 Academia. All rights reserved