Classification of instagram fake users using supervised machine learning algorithms

Abstract

On Instagram, the number of followers is a common success indicator. Hence, followers selling services become a huge part of the market. Influencers become bombarded with fake followers and this causes a business owner to pay more than they should for a brand endorsement. Identifying fake followers becomes important to determine the authenticity of an influencer. This research aims to identify fake users' behavior, and proposes supervised machine learning models to classify authentic and fake users. The dataset contains fake users bought from various sources, and authentic users. There are 17 features used, based on these sources: 6 metadata, 3 media info, 2 engagement, 2 media tags, 4 media similarity. Five machine learning algorithms will be tested. Three different approaches of classification are proposed, i.e. classification to 2-classes and 4-classes, and classification with metadata. Random forest algorithm produces the highest accuracy for the 2-classes (authentic, fake) and 4-classes (authentic, active fake user, inactive fake user, spammer) classification, with accuracy up to 91.76%. The result also shows that the five metadata variables, i.e. number of posts, followers, biography length, following, and link availability are the biggest predictors for the users class. Additionally, descriptive statistics results reveal noticeable differences between fake and authentic users.

Analysis and Prediction of Instagram Users Popularity using Regression Techniques based on Metadata, Media and Hashtags Analysis

“…For future work, methods to predict the authenticity or emotion of users can be incorporated, such as sentiment analysis, fake accounts detection [41], and malicious content detection [42]. It was proven that non-authentic users can behave differently from authentic users [41]. Image analysis can also be added, such as the image quality and category of a post.…”

Visual media analysis for Instagram and other online platforms

“…lack of profile picture; multiple followers with same creation date) and ratios (low like-to-follower ratio) to aid in the hunt (HypeAuditor, 2021), along with more elaborate techniques in the computational literature (Sen et al, 2018) (see Figure 2). It is often reminded that there is a percentage of inauthentic accounts that one has in one's follower account anyhow, especially influencers', who are 'bombarded with fake followers' (Purba et al, 2020(Purba et al, : 2763 and also are used (as well as recommended) as seed accounts for new users building a nascent profile.…”

“…The ranking of a website for the same query over time may be graphed, for example in the Issue Dramaturg project that portrayed the ‘drama’ of search engine space as a website, routinely returned at the top of the results, one day vanishes from the first 1000 returns, likely because of an algorithmic ‘update’ (Rogers, 2013). Changes over time to rankings are also visualised with RankFlow, where one compares how a number of websites or videos in YouTube, for example, wax and wane in the search engine returns (Rieder et al., 2018).…”

Realistic influence maximization based on followers score and engagement grade on instagram

“…This was done using Instagram API and various third-party Instagram websites. The users were cleaned using the fake user's classification model from an earlier study [23]. The raw data consists of 70,409 nodes/users, 1,007,107 edges/connections, 1,031,348 posts, and 47,689,496 likers entry.…”