An Efficient Method for Detection of Fake Accounts on the Instagram Platform

In recent years, online social networks (OSNs), such as Instagram, Twitter, and Facebook, have become popular platforms to disseminate and share information [1]. These services provide fast and suitable communication and other types of tools that make their users be able to directly share and publish their multimedia contents such as pictures, videos, and audios over the internet [2]. Hence, besides the significant number of users on social platforms, these features and tools have interested many cyber criminals in using them to perform their malicious activities on social media platforms effectively. Unlike in the past, many attacks with a limited or small effect can now have a considerable impact by using online social platforms [3].

However, social media's effect is significant in people's lives, and many people use them to build more extensive connections [4]. One of the most popular social media is Instagram [5]. Instagram is a free social networking app built for sharing photos and videos over the internet. It is similar to most other social media, where those who create an account have a profile and news feed and can share photos and videos through that.

In recent years, many celebrities and businesses have created their accounts on Instagram; they use Instagram to grow their business and fans [6]. Furthermore, many of them and other famous users use it as a platform for advertising. When someone is boosting the number of followers over a hundred thousand or millions, it is no surprise to use that person's account as a lucrative earner. In the last years, many celebrities and ordinary people who reached a considerable number of followers on Instagram have used their accounts as a place for advertising. People also try to increase the number of their followers for other reasons, such as achieving more fame, being trustworthy, and being influential.

Such versatility and spread of use have made Instagram the perfect platform for the proliferation of abnormal accounts, which behave in unusual ways. Most academic researchers have mostly focused on spammers and accounts, which put their efforts into spreading advertising, spam, malware, and other suspicious activities [7]. These malicious accounts are usually using automatic programs to improve their performance, hide their real identity, and look like real users. In past years, media have reported that account of celebrities, politicians, and some popular business has indicated suspicious inflation of followers. Fake Instagram accounts specifically used to increase the number of followers of a target account.

Therefore, artificially inflating the number of followers can also be concluded to obtain an account more influential and trustworthy in order to stand from the crowd to attain and attract more legitimate followers to their account [8]. In past years, some of the banks and financial institutions in the U.S. decided to analyze social media accounts of the loan applicants, before genuinely giving the loan. Hence, having a popular account can help effectively to increase the creditworthiness and reliability of the applicant. Furthermore, if a spammer adopted fake followers, it can effectively act as a legitimate user and post more authoritative messages and launch various efficient advertising campaigns [9].

Some professional users think fake account detection is an easy task with their rules based on anomaly account behavior. Though, such rules are usually matched neither with analytic algorithms to aggregate them nor with validation mechanisms. Most academic researchers have focused mainly on spam and bot detection in various social media like Facebook and Twitter, with brilliant results in classifying fake accounts based on their legitimate and fraudulent features, mainly utilizing machine-learning methods. However, the paper's remaining part proceeds as follows: the second section will give a brief overview of the previous research in fake and spam accounts detection in different environments and highlights their shortcomings and achievements. The third section describes the methodology used for this study, including the feature extraction, and dataset. The fourth section presents information about the proposed detection model, such as the used methods and detection process. The fifth section presents experiments such as a description of the experiment setup, conditions, and evaluation metrics used in the experiment. It also discusses the results and the research findings, besides comparing the results with other techniques. Finally, the sixth section sums up the paper with concluding remarks.

This section presented the collected Instagram accounts dataset, which was used to conduct our experiments in this research. Moreover, we have described how each of them was collected and how these accounts were verified and classified into fake and legitimate classes.

3.1 Data collection

Like most social media platforms, the public Instagram developer API only provides the public information of users. It is not possible to access some users' activities and login information, mostly when a user already has set that account to private mode. This problem is considered as an obstacle to the process of data collection. To solve the issues and crawl users' information, we have developed a specific data crawler and feature collection tool described in the following steps (see Figure 1).

1.png

Figure 1. Dataset and feature collection procedure

The 6868 regular users, such as celebrities, companies, and ordinary legitimate users, plus 3132 anomaly users who manually checked and selected, have collected in the dataset. We have developed two types of data crawlers for achieving regular and anomaly users, respectively. The ordinary user crawler has used Instagram's explore feature to identify regular users and add them to the list of ordinary users in the dataset. Instagram's Explore feature displays recent posted pictures and videos that reached other users' attention, which show accounts posted are mostly real and legitimate.

Furthermore, to discover and achieve fake users on Instagram, first, the developed crawler used to obtain fake users ID through the follower list of users who considered a considerable number of fake users in their follower list. In second, we have developed another tool to manually check all of the fake archived users in the dataset, be assured about their identity, and improve the dataset's quality.

Table 1. Description of the dataset

For each user, some public information crawled using Instagram API; the description of the dataset and list of the crawled features are listed in Tables 1 and 2, respectively.

The collected features are listed in the following Table 2.

Table 2. The list of collected features

Figure 2 illustrated four of the essential features in our dataset. Figure 2 (a) shows the distribution of accounts with a profile picture in the dataset, and it indicates most accounts that have not set profile pictures to their accounts belong to the fake category. Similarly, the number of followed by fake accounts are quite large, and most fake accounts followed more people than their followers, as shown in Figure 2 (b) and (c). It may be explained that most fake users created only to increase the number of followers of regular users and that is because many Instagram regular users try to buy fame using increase the number of their accounts followers.

Figure 2 (d) indicates the number of posts in each account. As expected, most fake accounts do not contain many posts or mostly have zero or one post because many of these accounts only aim at following other users or advertising, so their creator consumes a short time on the increasing number of their post or design appearance of them. However, the recent creator of these fake accounts tries to design their appearance and increase the number of their posts, so their accounts look more normal and satisfy their customers.

Furthermore, by this trick, they can sometimes bypass Instagram's limitations. Though, their account still has a small number of followers and a large number of following. Some of these fake account producers tried to decrease these vast differences between the numbers of their accounts followers and followed by using the other fake accounts they own. Accordingly, they make fake activities between their fake accounts and make their fake accounts which are mostly bots following each other to their number of followers look like regular users. Finally, all of their fake accounts will have some followers, and it helps them look more like regular users.

21.png

(a)

22.png

(b)

23.png

(c)

24.png

(d)

Figure 2. The distribution of four important features on the dataset

Feature analysis

Unlike normal Instagram users, fake users are usually aimed at commercial intent, such as advertisements spreading and following more users. This section randomly selected some of the fake users from the dataset and manually studied them. Therefore, an analysis of the differences between fake and legitimate users from both content and behavior points of view is discussed as follows:

(1): Most fake accounts do not contain a significant number of posts; many of them have zero or only a small number of posted pictures and videos.

(2): Almost all fake users follow a multitude of legitimate users. The main aim of fake accounts is to increase the number of followers of the other authorized users. Thus, most fake accounts followed a considerable amount of people, so they followed more people than they followed by. That makes the fraction of followed per followers huge in comparison with legitimate users.

(3): After analyzing some of the fake accounts, as expected, it indicates the considerable fraction of fake users did not set a picture to their profile, and also their profile does not contain a biography description more than the name they entered in the process of creating the account. The reason behind that is, most of the fake accounts only created for increasing the number of other users’ followers, and they use a limited time on the design of the account appearance. Though this is just for a fraction of fake accounts, and many of them seem legitimate users.

Table 5. Comparison of evaluation metrics between classifiers

Classifier	Precision		Recall		F-measure
	Fake	Normal	Fake	Normal	Fake	Normal
Hoeffding Tree	0.932	0.979	0.954	0.968	0.943	0.974
Random Tree	0.954	0.980	0.957	0.979	0.955	0.980
RBF	0.897	0.975	0.947	0.950	0.921	0.963
MLP	0.983	0.977	0.952	0.992	0.967	0.985
SVM	-	0.687	0.0	1.0	-	0.814
Naïve Bayes	0.873	0.985	0.968	0.935	0.918	0.960
Bagged Decision Tree	0.982	0.985	0.968	0.992	0.975	0.989

 

4.png

Figure 4. Comparison between F-measure, Recall and Precision results

5.png

Figure 5. Receiver operating characteristic curve for the legitimate class

Table 5 illustrates the value of evaluation metrics in which precision, recall, and F-measure are measured for fake and legitimate accounts. Moreover, we have compared the proposed approach to other well-known classifiers: Random tree, J48, SVM, Naïve Bayes, and Hoeffding tree. The comparison between the proposed method and the mentioned algorithms is presented in Table 5.

As shown in Tables 4 and 5, we see that the bagging decision tree-based algorithm produced better performance than the other five classification algorithms. It successfully classified 98.45 of accounts with 1.55% misclassified, respectively. After the bagging algorithm, the MLP, Random Tree, and Hoeffding Tree algorithms obtained the highest performance on the dataset with a 97.9, 97.2%, and 96.38% classification accuracy. The RBF and Naive Bayes produced almost the same results, with an accuracy of 94.92% and 94.58%. The SVM algorithm obtained the lowest accuracy of 0.613, respectively. As presented in Table 4, the other four considered algorithms also achieved good detection accuracy. This is because of distinctive useful features (including content and user behavior) helps classification algorithms effectively distinguish fake users from legitimate ones. However, Figure 4 describes precision, recall, and F-measure ratios obtained by the model to illustrate the difference between each of the criteria better.

Figure 5 represents the result of the receiver operating characteristic (ROC) curve. ROC curve is a useful tool for visualization that can decide whether a model is suitable regarding cost sensitivity. In the represented (ROC) curve, the curve’s x-axis denotes the false positive rate while the y-axis describes the false negative. The area found under the curve with the value of (0.989) shows that it is a suitable model.

In the next test, we classified accounts using each feature independently; this method is not very common but lets us find the influence of each feature's impact on detecting fake accounts independently. The following two tables provide the information about the F-measure, accuracy, best feature type, and full feature set results on the datasets with different user accounts.

Table 6. Best feature types across different size of datasets

The results obtained in Table 6 demonstrate the feature type "Postcount" performed better than other features, which shows the number of account posts has a significant role in identifying the legitimacy of the Instagram accounts since many spammers who create fake accounts spend less time designing account appearances. Moreover, as shown in Table 7, there is a progressive increase in accuracy and F-measure ratios as the dataset size increases.

Table 7. The Full set of features results across different size of datasets

6.png

Figure 6. Accuracy versus the number of accounts across datasets

7.png

Figure 7. F-measure versus the number of accounts across datasets

Figures 6 and 7 show the changes in F-measure and accuracy as the number of accounts have increased over the datasets.

As shown in Figure 6, there is a progressively decrease in best feature accuracy results as the dataset size increases. This shows the role of the best feature in the final result gets lower when dataset size increases. Moreover, a gradual increase in accuracy levels of full features set results as the number of accounts is increased across the datasets. This increase is a sign that the features used perform satisfactorily across the data sets. We have only worked with a dataset of 10000 Instagram accounts, and the exhibited trends show that if the dataset size has increased, the accuracy could improve further. We present the F-measure trends over the dataset in Figure 7.

We can observe in Figure 7 that there has been a decrease in best feature F-measure results while there is progressively increasing in full features set results as the dataset size increases. This is similar to the accuracy trends obtained earlier in Figure 6.