Social Networks User Types, Models - Article Example

Study of Social Networks User Types, Models and New Features Using Pattern Recognition and Data ification Techniques Social networking sites have become an integral part of communication. Due to its numerous advantages, these sites are considered to be one of the easiest modes of communication. This paper deals with the various user types and the models of social networking. It also specifies the data classification and data mining techniques which provide the intended data security and privacy. This paper provides a detailed description about the pattern recognition techniques that improves the efficiency of the social networking sites. I. SOCIAL NETWORKING USER TYPES Social networking users are generally classifies into six types. These types of users are classified based on their personality and its types. The various types of social networking users are essentialist, transumers, connectors, scene-breakers, collaborators and entrepreneurs. The essentialists are people who make use of the social networking sites to be in contact with their family and friends. The next category, transumers are people those who adhere to the trends. These people implement the latest improvements and innovations in the technology. Connectors are the next category of users who look out for creative trends and other unique features of the social networking sites. Around 10 percent of the social networking users are classified as connectors. Scene-breakers are the next category of users who are interested in learning new concepts. They are regular browsers in the social networking sites and they communicate their talent to the other users in the social networking sites. Another set of users are collaborators who work for the integration of users to create and explore new projects. They form a group to create and develop new events and they are knows as online traders. The final group of users is the netrepreneurs who browse through the social networking sites. They make up to 4 percent of the social networking users. These are the six different types of social networking users. The basic social networking models rely on the presentation of each and every user. Then the relationship among the other users are established which enables the user to find the person whom he intends to. II. FEATURES The social networking sites incorporate various new features and implement the latest updates on their sites. The advancements in the technologies are used in the development and improvement of social networking sites like facebook, linkedin and orkut. The features of such social networking sites include creating personal profiles, user images and the communication with the help of text. The networking sites allow the users to create personal profiles with their name, date of birth, location and their personal interests. This enables the other users to easily identify a particular person in the networking site. The next best feature is the ability to upload personal images that helps others to easily find and track the person whom they are searching for. The most important feature of a social networking site is that it facilitates the users to send messages in the form of text, graphics and sounds. This makes the communication process much easier. The objective of a social networking site is to establish connectivity among the people and to communicate with them in a hassle free manner. With the advent of such social networking sites a user can interact, communicate, perform an activity and form groups which are referred to as communities. II. DATA CLASSIFICATION TECHNIQUES Apart from these common features several other features are introduced using the data classification techniques. The data classification techniques classify the data by dividing them into quantiles, equal intervals and natural breaks. The social networking sites implement these data classification techniques to classify the information regarding the users [3]. The users are classified based on their way of usage, type of usage and the purpose. The quantile method classifies the users depending on their category of usage and each unique class comprises of equal number of users. This enables the network administrator to identify the type of users and this can be done within a short period of time. The next classification technique, equal intervals divides the users in to two groups which comprises of equal number of users. The data mining techniques are implemented in most of the social networking sites to improve their efficiency and to implement the new features. The data mining techniques and the classification methods make use of iterative algorithms that enable the developers to identify the various models and to classify the users. The clustered data mining technique identifies the users with similar information. This technique helps the user to search for a person from a particular category. The privacy and security of the users form the integral part of any social networking site. To maintain these aspects the various data mining techniques are implemented [1]. The aim of a social networking site is to maintain the information pertaining to a particular user in a secured manner. Data validity is also an important part of a social networking site and this is achieved by collecting a valid email address from each and every user. III. PATTERN RECOGNITION TECHNIQUES Pattern recognition techniques are widely used in the creation of social networking sites. The data provided by the social networking users can be analyzed with the pattern recognition techniques [5]. This technique helps to identify the patterns that have not been previously used in the particular social networking site. V. DATA MINING STRATEGIES Data mining is generally known as a technique to extract particular information from an extensively large database. The data mining strategies like classification, filtering of contents and data clustering helps the developers to prevent data loss [4]. Apart from classification, prediction is also an efficient technique. The content filtering option makes sure that the data provided in the networking site is authentic. This helps them to identify the hackers which in turn reduce the number of security threats and attacks [2]. Surveys reveal that people between the age group of 17-25 access the social networking sites when compared to people of other age group. Figure 1: Steps of Data mining process. The data mining methodology is used to search a particular profile in a social networking site. This is achieved by implementing the data mining techniques to process the user's requests. Figure 2: Graph depicting the age of people with respect to the percentage of profiles. VI RECOMMENDATION The social networking sites must implement the data mining techniques like classification and clustering. LinkedIn must implement the clustering technique to find the profile of a hacker. This will enable in the efficient processing of the website. Case Study LinkedIn is one of the popular social networking sites that implement the various data mining techniques. This social networking site must implement the data mining techniques like classification and clustering to identify the types of users. Pattern recognition techniques should be used to differentiate the old patterns and the data that are created without any specific pattern. The various data classification methods will assist them to segregate the data and this would be helpful in providing a secure environment. LinkedIn offers better data security and privacy which can be made more efficient by implementing the data mining techniques. REFERENCES [1] Carrington, P and Scott, J. (2005) "Models and Methods in Social Network Analysis", [2] Wasserman, S and Faust, K. (1994) " Social Network Analysis: Methods and Applications", Structural Analysis in Social Sciences, Vol.8. [3] Han, J and Kamber, M. (2006). "Data Mining Concepts and Techniques", pp. 21-23. [4] Witten, I and Frank, E. (2005). "Data Mining: Practical Machine Learning Tools and Techniques", Vol. 2, pp. 254-255. [5] Theodoridis, S and Koutroumbas, K. (2009). "Pattern Recognition", Vol. 4, pp. 1-3. [6] Gross, R and Acquisiti, A. (2005). "Information Revelation and Privacy in Online Social Networks". Read More