Psychological Disorders Detection via Online Social Network Mining

Abstract

Now a day’s popularity of social networking sites leads to the problematic usage. An increasing number of psychological disorders in social networks, dependence on cybernetic relationships, information overload, and Net Compulsion have been reported recently. Symptoms of these psychological disorders are usually observed passively. In this situation, we argue that online social behaviour extraction offers an opportunity to actively identify disorder at an early stage.

It is difficult to identify the disorder because the psychological factors considered in standard diagnostic criteria questionnaire cannot be observed by the registers of online social activities. Our approach, New and innovative for the practice of disorder detection, it does so do not trust the self-disclosure of those psychological factors through the questionnaires.

Instead, we propose a machine learning approach that is detection of psychological disorders in social networks which exploits the features extracted from social network data for identify with precision possible cases of disorder detection. We perform an analysis of the characteristics and we also apply machine learning classifier in large-scale data sets and analyse features of the three types of psychological disorders.

Make sure your essay is 100% unique

Our experts will write for you an essay on any topic, with any deadline and requirements from scratch

127 our experts are available
right now

Get custom essay

Keywords – Online social network (OSN), mental disorder detection, feature extraction, SNMD Classifier.

Introduction

Online social network (OSN) they have become part of the daily life of many people. While OSN Apparently, it expands its users’ ability to increase social networks contacts, they can effectively diminish interpersonal contact Interactions in the real world. Studies show that some people’s behaviour is more audacious in the OSN because they can be put a mask when you communicate with other people there that is, hiding who I really am.

Psychological disorder is becoming a threat to people’s health now a days. With the rapid pace of life, more and more people are feeling mentally disturb. It is not easy to detect user’s psychological disorder in an early time to protect user. With the fame of web-based social networking, individuals are used to sharing their day by day activities and interacting with friends via web-based networking media stages, making it possible to use online social network data for mental disorder detection.

In our system, we find that users disorder state is closely related to that of his/her friends in social media, and we employ a large-scale dataset from real-world social platforms to systematically study the correlation of users’ disorder states and social interactions. We first define a set of psychological disorder-related textual and social attributes from various aspects. Fast pace of life, progressively and more individuals are feeling stressed.

Psychological disorder itself is non-clinical and common in our life, excessive and chronic disorder can be rather harmful to people’s physical and mental health. Users’ social interactions on social networks contain useful cues for stress detection. Social psychological studies have made two interesting observations. The first is mood contagion: a bad mood can be transferred from one person to another during social interaction. The second Social Interaction: people are known to social interaction of user.

The advancement of social networks like Twitter, Facebook an ever increasing number of people will share their every day events and moods, and interact with friends through the social networks. We can classify using machine learning framework. Due to leverage both Facebook post content attributes and social interactions to enhance mental disorder detection. After getting disorder level, system can recommended user hospital for further treatment, we can show that hospital on map and system also recommended to take precaution for avoid stress.

Related Work

In this section, we briefly review the related work on psychological disorder detection system and their different techniques.

Lot of work has been done in this field because of its extensive usage and applications. In this section, some of the approaches which have been implemented to achieve the same purpose are mentioned. These works are majorly differentiated by the algorithm for psychological disorder detection systems.

Existing works demonstrated that leverage social media for healthcare, and in particular mental disorders detection is feasible. There are some limitations exist in Facebook content based psychological disorder detection. Users do not always express their states directly in Facebook post. Although no disorder is revealed from the post itself, from the follow-up interactive comments made by the user and her friends, we can find that the user is actually stressed from work. Thus, simply relying on a user’s Facebook post content for mental disorders detection is insufficient. Users with high psychological disorders may exhibit low activeness on social networks.

Computer programs It should not be in the business to decide which questions are worthy of study. Though Hessians that are not non-viable are sometimes signs of misguided and meaningless questions inadequate models, or estimators, also occur frequently when information about the quantities of interest exist in the data through the probability function. The authors explain the problem in detail and present two preliminary proposals on how deal with non-invertible hessians without changing the question asked [3].

In the social network of Facebook to capture this notion. We find that links in the activity network tend to come and go. Quickly over time, and the strength of the bonds exhibits a reduce the decreasing tendency of the activity as a connection of a social network centuries. For example, only 30% of Facebook user pairs interact. Constantly from one month to the next. It is interesting to note that we also find this, even if the connections of the activity network many properties of graph theory change rapidly over time. The network of activities remains unchanged [5].

This paper is about a novel problem of emotion prediction in social networks. A method referred to as Mood cast for modelling and predicting emotion dynamics in the social network. The proposed approach can effectively model each user’s emotion status and the prediction performance is better than several baseline methods for emotion prediction. It is used to due to the limited number of participants. For model learning, it uses a Metropolis-Hastings algorithm to obtain an approximate solution. Experimental results on two different real social networks demonstrate that the proposed approach can effectively model each user’s emotion status and the prediction performance is better than several baseline methods for emotion prediction [10].

Literature Survey

Literature survey is the most important step in any kind of research. Before start developing we need to study the previous papers of our domain which we are working and on the basis of study we can predict or generate the drawback and start working with the reference of previous papers.

In this section, we briefly review the related work on mental disorder detection system and their different techniques.

1. “Psychological stress detection from cross-media microblog data using deep sparse neural network.” In proceedings of IEEE International Conference on Multimedia & Expo, 2014. H. Lin, J. Jia, Q. Guo, Y. Xue, J. Huang, L. Cai, and L. Feng. – This framework, the proposed method can help to automatically detect psychological stress from social networks.
2. “Daily stress recognition from mobile phone data, weather conditions and individual traits” pp.2014 Andrey Bogomolov, Bruno Lepri, Michela Ferron, Fabio Pianesi, and Alex Pentland – We have Studies about Daily stress recognition from mobile phone data, weather conditions and individual traits
3. Social comparison, envy, and depression on Facebook: a study looking at the effects of high comparison standards on depressed individuals. Journal of Social and Clinical Psychology, 2015 H. Appel, J. Crusius, and Alexander L. Gerla – This paper show depressed users are frequently found other than envy and self-esteem individuals.
4. “Real-Time Top-R Topic Detection on Twitter with Topic Hijack Filtering”, 2015 Kohei Hayashi† Takanori Maehara§ Masashi Toyoda Ken-ichi Kawarabayashi – In this work, we integrate both the extraction of significant problems. And filtering messages via Twitter.
5. “A framework for classifying online mental health-related communities with an interest in depression’ IEEE Journal of Biomedical and Health Informatics, 2016. B. Saha, T. Nguyen, D. Phung, and S. Venkatesh. – In this paper, a patient with an anxiety disorder can also develop depression. This concomitant mental health condition provides attention for our work in the classification of online communities with an interest in depression
6. “Subconscious Crowdsourcing: A Feasible Data Collection Mechanism for Mental Disorder Detection on Social Media” 2016. Chun-Hao Chang, Elvis Saravia, Yi-Shin Chen – In this paper, our goal is to build predictive models that exploit them Language and behaviour patterns, used especially in the social sphere .average, to determine if a user suffers from two cases of mental disorder.
7. “Machine Learning Framework for the Detection of Mental Stress at Multiple Levels” IEEE access, 2017 Ahmad Rauf Subhani, Wajid Mumtaz, Mohamad Naufal b Mohamad Saad, Nidal Kamel and Aamir Saeed Malik- The main contribution of this paper lies in developing an experimental paradigm for successfully inducing stress at multiple levels and providing a framework involving EEG data analyse for the identification of stress at multiple levels.
8. “A Comprehensive Study on Social Network Mental Disorders Detection via Online Social Media Mining” IEEE transactions, 2018 Hong-Han Shuai, Chih-Ya Shen, De-Nian Yang, – In this paper, we argue that mining online social behaviour provides an opportunity to actively identify SNMDs at an early stage.

This paper is about an automatic stress detection method from cross-media micro blog data. Three-level framework for stress detection from cross-media micro blog data. By combining a Deep Sparse Neural Network to incorporate different features from cross-media micro blog data, the framework is quite feasible and efficient for stress detection. This framework, the proposed method can help to automatically detect psychological stress from social networks. The future scope plan to investigate the social correlations in psychological stress to further improve the detection performance [6].

In the paper of mental stress recognition from mobile phone data, weather conditions and individual traits. That day by day stress can be dependably perceived in the form of behavioural measurements, get information from the client’s cell phone, for example, the climate conditions (information relating to short lived properties of the condition) and the identity attributes.

In work environments, where stress has become a serious problem affecting the productivity, leading to occupational issues and causing health diseases. Our proposed system could be extended and employed for early detection of stress-related conflicts and stress contagion, and for supporting balanced workloads [1].

In this work, we integrate both the extraction of significant problems. And filtering messages via Twitter. We develop a transmission algorithm for a frequency sequence of the document Tables; our algorithm allows real-time monitoring of the first 10. Topics of about 25% of all Twitter posts, while automatically Filtering of noisy and meaningless subjects. We apply ours proposed transmission algorithm for the flow of Japanese and Twitter successfully demonstrate that, compared to other non-negative online Matrix factorization methods, our structure keeps track of the real world. Events with high precision in terms of perplexity and Eliminates irrelevant topics [4].

Mental disorders often occur in combinations, for example A patient with an anxiety disorder can also develop depression. This concomitant mental health condition provides attention for our work in the classification of online communities with an interest in depression. For this, we traced a large body of 620,000. Publications made by 80,000 users in 247 online communities.

We have the psycho-linguistic themes and characteristics expressed in. The publications, using them as input for our model. Following a car Technique of learning, we have formulated a joint modeling. Framework for coexisting classifications related to mental health online community of these characteristics. In the end, we perform empirical validation of the model in the data set drawn where our model exceeds the latest avant-garde basic lines [11].

Mental disorders are affecting millions of people different cultures, age groups and geographic areas r. The challenge of mental disorders is that they are Difficult to detect in suffering patients, thus presenting an Alarming number of undetected cases and incorrect diagnosis. In this paper, our goal is to build predictive models that exploit them Language and behaviour patterns, used especially in the social sphere. average, to determine if a user suffers from two cases of mental disorder.

These predictive models are possible using a new data collection process, coined as a subconscious. Crowdsourcing, which helps you collect more quickly and reliably. Patient data set. Our experiments suggest that mining specific linguistic models and characteristics of social interaction of Reliable patient data sets can contribute significantly to further analysis and detection of mental disorders [2].

Mental disorders often occur in combinations, for example a patient with an anxiety disorder can also develop depression. This concomitant mental health condition provides attention for our work in the classification of online communities with an interest in depression. For this, we traced a large body of 620,000. Publications made by 80,000 users in 247 online communities. We have the psycho-linguistic themes and characteristics expressed in. The publications, using them as input for our model. Following a car Technique of learning, we have formulated a joint modelling. Framework for coexisting classifications related to mental health online community of these characteristics. In the end, we perform empirical validation of the model in the data set drawn where our model exceeds the latest avant-garde basic lines [1].

Proposed Approach

We develop new approaches for detecting psychological disorder cases of OSN users. We argue that mining social network data of individuals, as a complementary alternative to the conventional psychological approach, provides an excellent opportunity to actively identify those cases at an early stage. In this paper, we develop a machine learning framework for detecting psychological disorder users, namely Social Network Psychological Disorder Detection.

In proposed system approach, we formulate the task as classification problem to detect three types of social network psychological disorder detection using Machine learning approach:

1. Cyber-Relationship Addiction, which shows addictive behavior for building online relationships.
2. Net Compulsion, which shows compulsive behavior for online social gaming or gambling
3. Information Overload, which is related to uncontrollable surfing

By exploiting machine learning techniques with the ground truth obtained via the current diagnostic practice in Psychology, we extract and analyse several features of different categories from OSNs, including par asocial relationships, online and offline interaction ratio, social capital, disinhibition, self-disclosure, and bursting temporal behaviour. These features capture important factors or serve as proxies for disorder detection.

Conclusion

In this paper, automatically identify potential online users with psychological disorder. Psychological Disorder Detection is threatening people’s health. It is non-trivial to detect psychological disorder timely for proactive care. Therefore we presented a framework for detecting user’s psychological Disorder states from user’s social media data, leveraging Facebook post content as well as user’s social interactions. Employing real-world social media data as the basis, we studied the correlation between users’ psychological Disorder states.

References

1. B. Saha, T. Nguyen, D. Phung, and S. Venkatesh. A framework for classifying online mental health-related communities with an interest in depression. IEEE Journal of Biomedical and HealthInformatics, 2016.
2. Chun-Hao Chang, Elvis Saravia, Yi-Shin Chen “Subconscious Crowdsourcing: A Feasible Data Collection Mechanism for Mental Disorder Detection on Social Media” 2016.
3. J. Gill and G. King. What to do when you’re Hessian is not invertible: Alternatives to model specification in nonlinear estimation. Sociological Methods and Research, 2004.
4. Kohei Hayashi† Takanori Maehara§ Masashi Toyoda Ken-ichi Kawarabayashi “Real-Time Top-R Topic Detection on Twitter with Topic Hijack Filtering”,2015
5. B. Viswanath, A. Mislove, M. Cha, and K. P. Gummadi. On the evolution of user interaction in Facebook. WOSN, 2009.
6. H. Lin, J. Jia, Q. Guo, Y. Xue, J. Huang, L. Cai, and L. Feng. “Psychological stress detection from cross-media microblog data using deep sparse neural network. “ In proceedings of IEEE International Conference on Multimedia & Expo, 2014.
7. Liqiang Nie, Yi-Liang Zhao, Mohammad Akbari, Jialie Shen, and Tat-Seng Chua.” Bridging the vocabulary gap between health seekers and healthcare knowledge.” Knowledge and Data Engineering, IEEE Transactions on, 27(2):396–409, 2015.
8. Chi Wang, Jie Tang, Jimeng Sun, and Jiawei Han.” Dynamic social influence analysis through time-dependent factor graphs.” Advances in Social Networks Analysis and Mining (ASONAM), 2011 International Conference on, pages 239 – 246, 2011.
9. Lexing Xie and Xuming He. “Picture tags and world knowledge: learning tag relations from visual semantic sources. “In ACM Multimedia Conference, pages 967–976, 2013.
10. Yuan Zhang, Jie Tang, Jimeng Sun, Yiran Chen, and Jinghai Rao. “Moodcast: Emotion prediction via dynamic continuous factor graph model. “2013 IEEE 13th International Conference on Data Mining, pages 1193–1198, 2010.