CN110059498B - Privacy control automatic setting method and system for social network - Google Patents

Privacy control automatic setting method and system for social network Download PDF

Info

Publication number
CN110059498B
CN110059498B CN201910216242.7A CN201910216242A CN110059498B CN 110059498 B CN110059498 B CN 110059498B CN 201910216242 A CN201910216242 A CN 201910216242A CN 110059498 B CN110059498 B CN 110059498B
Authority
CN
China
Prior art keywords
privacy
user
personal
text information
attribute
Prior art date
Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
Active
Application number
CN201910216242.7A
Other languages
Chinese (zh)
Other versions
CN110059498A (en
Inventor
曹娟
郭俊波
谢添
刘浩远
吕博
王蕊
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Institute of Computing Technology of CAS
Original Assignee
Institute of Computing Technology of CAS
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by Institute of Computing Technology of CAS filed Critical Institute of Computing Technology of CAS
Priority to CN201910216242.7A priority Critical patent/CN110059498B/en
Publication of CN110059498A publication Critical patent/CN110059498A/en
Application granted granted Critical
Publication of CN110059498B publication Critical patent/CN110059498B/en
Active legal-status Critical Current
Anticipated expiration legal-status Critical

Links

Images

Classifications

    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F21/00—Security arrangements for protecting computers, components thereof, programs or data against unauthorised activity
    • G06F21/60—Protecting data
    • G06F21/62—Protecting access to data via a platform, e.g. using keys or access control rules
    • G06F21/6218—Protecting access to data via a platform, e.g. using keys or access control rules to a system of files or objects, e.g. local or distributed file system or database
    • G06F21/6245—Protecting personal data, e.g. for financial or medical purposes
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
    • G06Q50/00—Information and communication technology [ICT] specially adapted for implementation of business processes of specific business sectors, e.g. utilities or tourism
    • G06Q50/01—Social networking

Landscapes

  • Engineering & Computer Science (AREA)
  • General Health & Medical Sciences (AREA)
  • Theoretical Computer Science (AREA)
  • Health & Medical Sciences (AREA)
  • Physics & Mathematics (AREA)
  • Bioethics (AREA)
  • Business, Economics & Management (AREA)
  • General Physics & Mathematics (AREA)
  • Computer Hardware Design (AREA)
  • Marketing (AREA)
  • General Engineering & Computer Science (AREA)
  • Computer Security & Cryptography (AREA)
  • Databases & Information Systems (AREA)
  • Computing Systems (AREA)
  • Medical Informatics (AREA)
  • Economics (AREA)
  • Human Resources & Organizations (AREA)
  • Software Systems (AREA)
  • Primary Health Care (AREA)
  • Strategic Management (AREA)
  • Tourism & Hospitality (AREA)
  • General Business, Economics & Management (AREA)
  • Information Transfer Between Computers (AREA)
  • Storage Device Security (AREA)
  • Telephonic Communication Services (AREA)

Abstract

The invention provides a privacy control automatic setting method and a privacy control automatic setting system for a social network, which comprise the following steps: according to the visibility of each user attribute in the personal file of the user to be controlled in privacy, counting the personal public opening of the user to be controlled in privacy; acquiring a privacy attribute set consisting of a plurality of privacy attributes, acquiring text information to be issued of a user to be controlled in privacy, inputting the text information to a plurality of classifiers, wherein each classifier corresponds to one privacy attribute, the classifiers output probability distribution of the text information on values corresponding to the privacy attributes, and normalizing the entropy of the probability distribution to obtain the proper public aperture of the text information; obtaining the personal openness of each friend of the user to be controlled in privacy according to the personal profile and the release content of the friend of the user to be controlled in privacy; and measuring the privacy sensitivity of the text information to each friend according to the personal public degree, the suitable public degree and the personal public degree of the friends of the user, and determining the public range of the text information according to the privacy sensitivity.

Description

Privacy control automatic setting method and system for social network
Technical Field
The invention relates to privacy protection of a social network, in particular to a method and a system for automatically setting privacy control of a social network according to user information.
Background
The rapid development of Online Social Networks (OSNs) in recent years has facilitated person-to-person communication and accelerated information dissemination. Meanwhile, the number of interactions among users is increased, and improper privacy setting can cause personal information to be diffused to an unforeseen range, so that the privacy of the individual is threatened, and a plurality of privacy-related problems are generated.
While most OSNs, such as microblogs, Twitter, various types of forums, etc., provide privacy settings for attributes in a personal profile, such as all visible, grouped visible, only self visible, etc., such settings are typically default to all visible, and the location of most privacy settings is not obvious. In addition, when a user publishes information, the default privacy settings are also visible to all, and cannot be automatically adjusted according to the published content of the user, so that the user can unconsciously reveal own privacy.
Disclosure of Invention
Aiming at the defects of the prior art, the invention provides an automatic privacy control setting method for a social network, which comprises a measuring method for measuring the privacy protection degree of attributes in a user personal file, the degree of privacy-related information contained in user release content and the privacy protection degree of friends of the user, and provides the automatic privacy control setting method for the user release content by combining the measuring values of the three.
Specifically, the invention provides a privacy control automatic setting method for a social network, which comprises the following steps:
step 1, according to the visibility of each user attribute in the personal file of a user to be subjected to privacy control, counting the personal public opening degree of the user to be subjected to privacy control;
step 2, acquiring a privacy attribute set consisting of a plurality of privacy attributes, acquiring text information to be issued by a user to be controlled in privacy, inputting the text information to a plurality of classifiers, wherein each classifier corresponds to one privacy attribute, the classifiers output probability distribution of the text information on values corresponding to the privacy attributes, and the entropy of the probability distribution is normalized to obtain the suitable public aperture of the text information;
step 3, obtaining the personal openness of each friend of the user to be controlled in privacy according to the personal profile and the release content of the friend of the user to be controlled in privacy;
and 4, measuring the privacy sensitivity of the text information to each friend according to the personal public degree of the user, the suitable public degree and the personal public degree of the friend, and determining the disclosure range of the text information according to the privacy sensitivity.
The privacy control automatic setting method for the social network is characterized in that the specific statistical mode of the personal public degree of the user in the step 1 is as follows:
Figure BDA0002002179660000021
wherein U is the personal public opening of the user, wuiRepresents the weight value corresponding to the user attribute i, and sigmaiwui＝1，viIndicating the visibility of the attribute i.
The privacy control automatic setting method for the social network, wherein the determination mode of the suitable disclosure degree in the step 2 is as follows:
Figure BDA0002002179660000022
Figure BDA0002002179660000023
wherein C is the proper opening degree, pijAs privacy attributes SiProbability distribution over values, niRepresenting privacy attributes SiThe number of values, wci, represents the privacy attribute SiAnd satisfies Σiwci＝1。
The privacy control automatic setting method for the social network is characterized in that the determination mode of the personal disclosure degree of the friend i in the step 3 is as follows:
Figure BDA0002002179660000024
wherein, UiPersonal public opening, sigma, for the user of the friend ijCj/ncUsed for measuring the degree of disclosure of privacy sensitive information in the content issued by friend i, ncTotal number of contents released for friend i, CjIndicating the privacy sensitivity of the jth text published by the buddy.
The privacy control automatic setting method for the social network is characterized in that the privacy sensitivity measuring mode of the friend i in the step 4 is as follows:
Mi＝U*C*Fi
wherein M isiPrivacy sensitivity for friend i.
The invention also provides a privacy control automatic setting system for the social network, which comprises the following steps:
the module 1 is used for counting the personal public degree of a user to be subjected to privacy control according to the visibility of each user attribute in the personal file of the user to be subjected to privacy control;
the module 2 acquires a privacy attribute set consisting of a plurality of privacy attributes, acquires text information to be issued by a user to be controlled in privacy, inputs the text information to a plurality of classifiers, each classifier corresponds to one privacy attribute, the classifiers output probability distribution of the text information on values corresponding to the privacy attributes, and normalizes entropy of the probability distribution to obtain suitable public aperture of the text information;
the module 3 is used for obtaining the personal openness of each friend of the user to be controlled in privacy according to the personal profile and the release content of the friend of the user to be controlled in privacy;
and the module 4 measures the privacy sensitivity of the text information to each friend according to the personal public degree of the user, the suitable public degree and the personal public degree of the friend, and determines the disclosure range of the text information according to the privacy sensitivity.
The privacy control automatic setting system for the social network is characterized in that the specific statistical mode of the personal public degree of the user in the module 1 is as follows:
Figure BDA0002002179660000031
wherein U is the personal public opening of the user, wuiRepresents the weight value corresponding to the user attribute i, and sigmaiwui＝1，viIndicating the visibility of the attribute i.
The privacy control automatic setting system for the social network, wherein the determination mode of the suitable disclosure degree in the module 2 is as follows:
Figure BDA0002002179660000032
Figure BDA0002002179660000033
wherein C is the proper opening degree, pijAs privacy attributes SiProbability distribution over values, niRepresenting privacy attributes SiThe number of values, wci, represents the privacy attribute SiAnd satisfies Σiwci＝1。
The privacy control automatic setting system for the social network, wherein the determining mode of the personal disclosure degree of the friend i in the module 3 is as follows:
Figure BDA0002002179660000034
wherein, UiPersonal public opening, sigma, for the user of the friend ijCj/ncUsed for measuring the degree of disclosure of privacy sensitive information in the content issued by friend i, ncTotal number of contents released for friend i, CjIndicating the privacy sensitivity of the jth text published by the buddy.
The privacy control automatic setting system for the social network is characterized in that the privacy sensitivity measuring mode of the friend i in the module 4 is as follows:
Mi＝U*C*Fi
wherein M isiPrivacy sensitivity for friend i.
From the above solution, the present invention includes: based on the analysis of the user, the default visible range of each attribute in the personal profile page of the user and the content published by the user are set, and the default visible range of the content to be published is set according to the privacy preference and the friend privacy protection degree of the user. The invention has the advantages that: when a user publishes content, an automatic privacy control setting method is provided, and a sharing strategy for protecting the privacy of the user is provided for the content publishing at this time according to the personal privacy preference, the published content and the privacy protection degree of friends of the published content. Compared with the prior art, the privacy protection strategy is more flexible, and the user does not need to manually set the privacy for each sharing.
Drawings
FIG. 1 is a flow chart of the present invention.
Detailed Description
The invention aims to provide a strategy for automatically setting privacy control, and the privacy leakage problem caused by information sharing is relieved.
The invention divides the privacy control of the user into two parts: privacy control of attributes in a user's personal profile and privacy control of the user's published content. According to the invention, default settings which can protect privacy better are provided for the two types of privacy control according to the user information.
First, privacy control of attributes in a user's personal profile.
Aiming at a platform with specific application, two types of statistical methods are adopted according to the number of active users of the platform. If the platform has enough active users, the users are directly subjected to statistical analysis; otherwise, statistical analysis is performed by means of user data of other large OSNs (such as microblog, Twitter and the like). The active user definition is different according to different platforms, for example, for microblogs, users with a total number of microblogs larger than 30, account registration time longer than one month, and ratio of original microblogs to forwarded microblogs within a certain range can be defined as active users.
Analyzing the general view of the privacy sensitivity of the user to various attributes in the user file, and performing statistical analysis on each attribute (name, age, address, marital status, and the like). If the attribute has more than a preset number or proportion of users (e.g., half of the users) set to be invisible, the default privacy setting for the attribute is set to be visible only by itself.
The user can modify the visibility of the attributes in the personal profile of the user by himself, and the definition U is the disclosure degree of the information in the personal profile of the user and is used for the privacy setting of the subsequent user issued content. The calculation is as follows:
Figure BDA0002002179660000051
wherein, wuiRepresenting the weight value corresponding to the user attribute i and satisfying sigmaiwui＝1，viIndicates the visibility of the attribute i, when all people are visible viWhen a packet is visible, v ═ 1i0.5, when only visible to oneself vi0. Without loss of generality, here the attribute weights wuiAnd (4) evenly distributing.
Second, as shown in FIG. 1, the user publishes privacy controls for the content.
1. And calculating the degree of the privacy-related information contained in the user release content.
The invention only considers the privacy problem of the text information. Defining all privacy-sensitive attribute categories as a set S, and setting the set according to privacy terms of each large company, for example: a health condition; political, religious beliefs; age; sexual orientation; sex; disability; economic conditions, etc.
For text content, training multiple groups of classifiers based on a machine learning method, wherein each classifier corresponds to a privacy-sensitive attribute SiOutput vector piEach dimension of the vector represents a piece of text in an attribute SiProbability distribution p over each possible value jij. Calculating piNormalization to obtain Ei. For example: sensitivity attribute SiSuch as S1For 'age group', possible values are<20；20-40；>Three kinds of 40, ni3, vector pi＝[0.3,0.4,0.3]The probabilities corresponding to the three classes, respectively, and finally the entropy of the vector pi, n, is calculatediRepresents an attribute SiThe number of all possible values, then EiThe calculation is as follows:
Figure BDA0002002179660000052
Eithe smaller the size, the more the text is in the attribute SiThe lower the uncertainty, the easier it is to reveal the privacy of the attribute, whereas the weaker the representation is in relation to the attribute. Thus using EiMeasure the text to sensitivity attribute SiTo the extent appropriate for disclosure.
E for all sensitive attributesiWeighting to obtain C:
Figure BDA0002002179660000053
wherein wci represents the weight of each attribute, and satisfies Σiwci1. C represents the comprehensive consideration of various sensitive attributes, and the text is suitable for the disclosure degree. The closer C is to 1, the more irrelevant the content is to the privacy sensitive attributes, and the more suitable it is for disclosure from the privacy protection perspective. Without loss of generality, here the class weights are equally distributed.
2. And measuring the privacy protection degree of friends of the user.
The degree of privacy protection of a user's friend is determined by the friend's user profile and the published content together to measure the privacy awareness of the user's friend i, i.e., the degree of reliability of the disclosure of the content to be published to the friend, using FiExpressed, the calculation is as follows:
Figure BDA0002002179660000061
wherein, UiIs the friend's U value, indicating the visibility of his personal profile, ΣjCj/ncFor measuring the degree of disclosure of privacy sensitive information in the content distributed by the user, ncTotal number of contents distributed thereto, CjAnd the privacy sensitivity of the jth text published by the friend is represented, and the average sensitivity of all published contents of the friend is measured after the privacy sensitivity is added and averaged.
FiThe higher the indication of the friend's privacyThe more conscious, the less privacy risk the published content is visible to the buddy.
3. The default visibility range for this information is set in conjunction with the user's past preferences.
Combining the metric values, calculating the metric value M of the contents to be released to the friend ii
Mi＝U*C*Fi
Setting a threshold value T when Mi>And T, setting the content to be published to be visible to the friend. Namely, when the user has weak privacy awareness (U is larger), the relation between text content and privacy sensitive attribute is smaller (C is larger), and the friend has strong privacy awareness (F)iLarger), the content that the user wants to publish is more likely to be disclosed to friend i.
The following are system examples corresponding to the above method examples, and this embodiment can be implemented in cooperation with the above embodiments. The related technical details mentioned in the above embodiments are still valid in this embodiment, and are not described herein again in order to reduce repetition. Accordingly, the related-art details mentioned in the present embodiment can also be applied to the above-described embodiments.
The invention also provides a privacy control automatic setting system for the social network, which comprises the following steps:
the module 1 is used for counting the personal public degree of a user to be subjected to privacy control according to the visibility of each user attribute in the personal file of the user to be subjected to privacy control;
the module 2 acquires a privacy attribute set consisting of a plurality of privacy attributes, acquires text information to be issued by a user to be controlled in privacy, inputs the text information to a plurality of classifiers, each classifier corresponds to one privacy attribute, the classifiers output probability distribution of the text information on values corresponding to the privacy attributes, and normalizes entropy of the probability distribution to obtain suitable public aperture of the text information;
the module 3 is used for obtaining the personal openness of each friend of the user to be controlled in privacy according to the personal profile and the release content of the friend of the user to be controlled in privacy;
and the module 4 measures the privacy sensitivity of the text information to each friend according to the personal public degree of the user, the suitable public degree and the personal public degree of the friend, and determines the disclosure range of the text information according to the privacy sensitivity.
The privacy control automatic setting system for the social network is characterized in that the specific statistical mode of the personal public degree of the user in the module 1 is as follows:
Figure BDA0002002179660000071
wherein U is the personal public opening of the user, wuiRepresents the weight value corresponding to the user attribute i, and sigmaiwui＝1，viIndicating the visibility of the attribute i.
The privacy control automatic setting system for the social network, wherein the determination mode of the suitable disclosure degree in the module 2 is as follows:
Figure BDA0002002179660000072
Figure BDA0002002179660000073
wherein C is the proper opening degree, pijAs privacy attributes SiProbability distribution over values, niRepresenting privacy attributes SiThe number of values, wci, represents the privacy attribute SiAnd satisfies Σiwci＝1。
The privacy control automatic setting system for the social network, wherein the determining mode of the personal disclosure degree of the friend i in the module 3 is as follows:
Figure BDA0002002179660000074
wherein, UiPersonal public opening, sigma, for the user of the friend ijCj/ncUsed for measuring the degree of disclosure of privacy sensitive information in the content issued by friend i, ncTotal number of contents released for friend i, CjIndicating the privacy sensitivity of the jth text published by the buddy.
The privacy control automatic setting system for the social network is characterized in that the privacy sensitivity measuring mode of the friend i in the module 4 is as follows:
Mi＝U*C*Fi
wherein M isiPrivacy sensitivity for friend i.

Claims (4)

1. A privacy control automatic setting method for a social network is characterized by comprising the following steps:
step 1, according to the visibility of each user attribute in the personal file of a user to be subjected to privacy control, counting the personal public opening degree of the user to be subjected to privacy control;
step 2, acquiring a privacy attribute set consisting of a plurality of privacy attributes, acquiring text information to be issued by a user to be controlled in privacy, inputting the text information to a plurality of classifiers, wherein each classifier corresponds to one privacy attribute, the classifiers output probability distribution of the text information on values corresponding to the privacy attributes, and the entropy of the probability distribution is normalized to obtain the suitable public aperture of the text information;
step 3, obtaining the personal openness of each friend of the user to be controlled in privacy according to the personal profile and the release content of the friend of the user to be controlled in privacy;
and 4, measuring the privacy sensitivity of the text information to each friend according to the personal public degree of the user, the suitable public degree and the personal public degree of the friend, and determining the disclosure range of the text information according to the privacy sensitivity.
2. The method according to claim 1, wherein the specific statistical manner of the personal public degree of the user in step 1 is as follows:
Figure FDA0002815588790000011
wherein U is the personal public opening of the user, wuiRepresents the weight value corresponding to the user attribute i, and sigmaiwui＝1，viIndicating the visibility of the ith attribute, v when the ith attribute is visible to alliWhen a packet is visible, v ═ 1i0.5, when only visible to oneself vi＝0。
3. A privacy control automatic setting system for a social network, comprising:
the module 1 is used for counting the personal public degree of a user to be subjected to privacy control according to the visibility of each user attribute in the personal file of the user to be subjected to privacy control;
the module 2 acquires a privacy attribute set consisting of a plurality of privacy attributes, acquires text information to be issued by a user to be controlled in privacy, inputs the text information to a plurality of classifiers, each classifier corresponds to one privacy attribute, the classifiers output probability distribution of the text information on values corresponding to the privacy attributes, and normalizes entropy of the probability distribution to obtain suitable public aperture of the text information;
the module 3 is used for obtaining the personal openness of each friend of the user to be controlled in privacy according to the personal profile and the release content of the friend of the user to be controlled in privacy;
and the module 4 measures the privacy sensitivity of the text information to each friend according to the personal public degree of the user, the suitable public degree and the personal public degree of the friend, and determines the disclosure range of the text information according to the privacy sensitivity.
4. The privacy-controlled automatic setting system for social networks according to claim 3, wherein the specific statistical manner of the personal public degree of the user in the module 1 is as follows:
Figure FDA0002815588790000021
wherein U is the personal public opening of the user, wuiRepresents the weight value corresponding to the user attribute i, and sigmaiwui＝1，viIndicating the visibility of the ith attribute, v when the ith attribute is visible to alliWhen a packet is visible, v ═ 1i0.5, when only visible to oneself vi＝0。
CN201910216242.7A 2019-03-21 2019-03-21 Privacy control automatic setting method and system for social network Active CN110059498B (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN201910216242.7A CN110059498B (en) 2019-03-21 2019-03-21 Privacy control automatic setting method and system for social network

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN201910216242.7A CN110059498B (en) 2019-03-21 2019-03-21 Privacy control automatic setting method and system for social network

Publications (2)

Publication Number Publication Date
CN110059498A CN110059498A (en) 2019-07-26
CN110059498B true CN110059498B (en) 2021-07-23

Family

ID=67317250

Family Applications (1)

Application Number Title Priority Date Filing Date
CN201910216242.7A Active CN110059498B (en) 2019-03-21 2019-03-21 Privacy control automatic setting method and system for social network

Country Status (1)

Country Link
CN (1) CN110059498B (en)

Citations (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN101655895A (en) * 2008-08-22 2010-02-24 株式会社日立制作所 Content control system
CN103268454A (en) * 2012-12-18 2013-08-28 北京奇虎科技有限公司 Display control method and system for data opened by user
CN104981816A (en) * 2013-02-19 2015-10-14 索尼电脑娱乐公司 Information processing system
CN105574434A (en) * 2015-12-14 2016-05-11 网易（杭州）网络有限公司 Information shielding method and device

Family Cites Families (7)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20120109836A1 (en) * 2010-11-01 2012-05-03 Google Inc. Content sharing interface for sharing content in social networks
US9781540B2 (en) * 2011-07-07 2017-10-03 Qualcomm Incorporated Application relevance determination based on social context
CN109040439B (en) * 2013-08-14 2021-01-12 华为终端有限公司 Method and device for realizing privacy protection
CN105262674B (en) * 2015-10-29 2018-09-25 小米科技有限责任公司 Method, apparatus, server and terminal for privacy authority to be arranged
CN106504101A (en) * 2016-10-11 2017-03-15 北京小米移动软件有限公司 The display control method for releasing news of social networking application and device
CN106528709A (en) * 2016-10-26 2017-03-22 北京小米移动软件有限公司 Social information recommendation method and apparatus
CN107665442B (en) * 2017-05-10 2020-03-27 平安科技（深圳）有限公司 Method and device for acquiring target user

Patent Citations (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN101655895A (en) * 2008-08-22 2010-02-24 株式会社日立制作所 Content control system
CN103268454A (en) * 2012-12-18 2013-08-28 北京奇虎科技有限公司 Display control method and system for data opened by user
CN104981816A (en) * 2013-02-19 2015-10-14 索尼电脑娱乐公司 Information processing system
CN105574434A (en) * 2015-12-14 2016-05-11 网易（杭州）网络有限公司 Information shielding method and device

Also Published As

Publication number Publication date
CN110059498A (en) 2019-07-26

Similar Documents

Publication Publication Date Title
KR102429416B1 (en) Anti-Cyber Bulling System and Method
US11023823B2 (en) Evaluating content for compliance with a content policy enforced by an online system using a machine learning model determining compliance with another content policy
US8145708B2 (en) On-line virtual robot (bot) security agent
US20080059198A1 (en) Apparatus and method for detecting and reporting online predators
US9805128B2 (en) Methods and systems for predicting psychological types
CN109074553A (en) It is handled using the spam of continuous model training
US10169476B2 (en) Method, apparatus, and computer-readable storage medium for grouping social network nodes
US20170351733A1 (en) User address match based on match quality
US8275656B2 (en) Maximum likelihood estimation under a covariance constraint for predictive modeling
JP2014219972A (en) System and method for detecting quitting intention on the basis of electronic-communication dynamics
KR101886628B1 (en) System and clustering method for group chatrooms, and service thereof
CN104484359B (en) A kind of the analysis of public opinion method and device based on social graph
Agdas et al. Wind speed perception and risk
Amintoosi et al. A trust framework for social participatory sensing systems
JP2023515067A (en) Method and apparatus for interactive and privacy-preserving communication between servers and user devices
KR101811751B1 (en) Advertisement providing server using chatbot
US20210234823A1 (en) Detecting and identifying toxic and offensive social interactions in digital communications
US20130117296A1 (en) Communication assistance device, communication assistance method, and computer readable recording medium
CN110059498B (en) Privacy control automatic setting method and system for social network
US10310698B2 (en) Information processing system, information processing method, information processing device, information processing terminal, for dynamically changing information that forms the basis of a displayed screen
KR101894060B1 (en) Advertisement providing server using chatbot
US11019020B2 (en) System and method for generating a user status and authenticating social interactions in a computer network
US20160225103A1 (en) Methods, systems, and computer readable media for determining social compatibility using a selected group
US9613148B2 (en) Method and system for determining property of user in social network platform
Rosemary et al. THE RELATIONSHIP BETWEEN ANONYMITY AND CYBER SEXUAL HARASSMENT BY TWITTER USERS: A CROSS-SECTIONAL STUDY

Legal Events

Date Code Title Description
PB01 Publication
PB01 Publication
SE01 Entry into force of request for substantive examination
SE01 Entry into force of request for substantive examination
GR01 Patent grant
GR01 Patent grant