SNS UNIT IV

UNIT IV PREDICTING HUMAN BEHAVIOUR AND PRIVACY ISSUES

Understanding and predicting human behaviour for social communities - User data
management - Inference and Distribution - Enabling new human experiences - Reality
mining - Context – Awareness- Privacy in online social networks - Trust in online
environment – What is Neo4j, Nodes, Relationship, Properties

1.0 Understanding and Predicting Human Behavior for Social Communities. Describe the
architectural framework and methodology for human behavior understanding and
prediction. (Nov/Dec'18)
However, despite all the technological revolutions, for the end user (Humans) it is
the perceived Quality of Experience (QoE) that counts, where QoE is a consequence of a
user’s internal state (e.g., predispositions, expectations, needs, motivation, mood), the
characteristics of the designed system (e.g., usability, functionality, relevance) and the
context (or the environment) within which the interaction occurs (e.g., social setting,
meaningfulness of the activity).
Dealing with the previously enumerated challenges and trying to achieve the
aforementioned goal, we propose an architectural framework and a methodology, which
together will pave the way to understand and predict human behavior in future social-aware
multimedia systems. Furthermore, our work overviews some application scenarios, which
could benefit from such innovation, namely advertising, augmented reality and self-
awareness systems.

1.1 User Data Management, Inference and Distribution

∙ Current service creation trends in telecommunications and web worlds are
showing the convergence towards a Future Internet of user-centric services.
∙ In fact, some works already provide user-oriented creation/execution environments,
but these are usually tied to specific scopes and still lack on the capability to adapt to
the heterogeneity of devices, technologies and the specificity of each individual user.
∙ Based on these limitations, the research identifies flexibility and personalization as the
foundation for users’ satisfaction, where the demand for different types of awareness
needs to be present across the entire value of chain of a service.
∙ Despite most initiatives require or propose some sorts of user profile management
systems; these are usually proprietary and include limited information about user
preferences and contexts.
∙ Therefore, in order to apply user information across a range of services and devices,
there is a need for standardization of user related data and the architecture that
enables their interoperability.
∙ These efforts have been seen at both fixed and mobile worlds and are usually taken
under the European Telecommunications Standards Institute (ETSI), the Third
Generation Partnership Project (3GPP), Open Mobile Alliance (OMA), among others.
∙ Considering data requirements from a wide range of facilities and from different
standardization organizations, the concept of Common Profile Storage (CPS) is
defined by 3GPP as a framework for streamlining service-independent user data and
storing it under a single
logical structure in order to avoid duplications and data inconsistency.
∙ Being a logically centralized data storage, it can be mapped to physically distributed configurations
and should allow data to be accessed in a standard format.
 ∙ Indeed, several approaches have been proposed to guarantee a certain interoperability degree and
can be grouped into three main classes: the syntactic, semantic and modeling approaches.
∙ The work proposes a combination of them to enable interoperability of user profile data
management for a Future Internet.
∙ Independently from the technology, all systems should allow user related data to be queried,
subscribed or syndicated and ideally through web service interfaces. However, standardization,
interoperability, flexibility and management are not the only challenges.
∙ To improve the degree of services personalization it is important to generate new information
from the existing one. In this sense, social networks, user modeling and reality mining techniques
can be empowered to study patterns and predict future behaviors.
∙ Consequently, all the adjacent data necessary to per- form such operations must be managed
within the scope of a user/human profile.
∙ Nevertheless, due to the sensitiveness of the information we are referring to, it is important to
efficiently control the way this information is stored, accessed and distributed, preserving users
privacy, security and trust.

With the aim of inferring users needs, desires or intentions, several research initiatives from
different fields (e.g., eHealth, Marketing, Telecoms) are starting to become a reality. Despite the
different methodologies and approaches, the user requirements and the technologies involved to
address the problems are usually the same.
∙ They commonly involve social network analysis, context-awareness and data mining. The basic
motivation is the demand to exploit knowledge from various amounts of data collected,
pertaining to social behavior of users in online environments.
∙ A prime example of this are the research efforts dedicated towards the Enron email dataset.
Together, these techniques proved to be useful for analysis of social network data, especially for
large datasets that cannot be handled by traditional methods.

Real world situations usually have to be derived from a complex set of features. Thus, context or
behavior aware systems have to capture a set of features from heterogeneous and distributed sources
and process them to derive the overall situation.
∙ Therefore, recent approaches are intended to be comprehensive, i.e., comprise all components and
processing steps necessary to capture a complex situation, starting with the access and
management of sensing devices, up to the recognition of a complex situation based on multiple
reasoning steps and schemes.
∙ To handle complex situations, the concept of decomposition is applied to the situation into a
hierarchy of sub-situations.
∙ These sub-situations can be handled autonomously with respect to sensing and reasoning. In this
way, the handling of complex situations can be simplified by decomposition.
∙ Another similar perspective is called layered reasoning, where the first stage involves feature
extraction and grouping (i.e., resulting in low-level context), the second event, state and activity
recognition (i.e., originating mid-level context), while the last stage is dedicated to prediction and
inference of new knowledge.
In this sense, combining all of pre-enunciated concepts with ontologies and semantic
technologies, we present a generic framework for managing user related data, which,
together with a specific methodology will pave the way to understandng and predicting future
human behavior within social communities.

1.2 Enabling New Human Experiences. (Discuss enabling New Human Experiences in detail and
reality Mining.9Apr/May'18)(Or)Explain the steps used for enabling human behavior
understanding and prediction.Nov-2019
After over viewing how the challenges related with the user data management and new
 knowledge inference are dealt, it is important to understand what are the technologies behind
it, how to link them and what can they achieve when combined in synergy. Altogether,
dealing with different aspects, they are capable of covering both the emotional and rational
aspects inherent to human behavior.

1.2.1 The
Technologies
1.2.1.1 Social
Networks
Humans in all cultures at all times form complex social networks; the term social network
here
means ongoing relations among people that matter to those engaged in the group, either for
specific reasons or for more general expressions of mutual solidarity. Likewise, social
networks among individuals who may not be related can be validated and maintained by
agreement on objectives, social values, or even by choice of entertainment. They involve
reciprocal responsibilities and roles that may be altruistic or self-interest based. Usually,
network members tend to trust and rely on each other, and to provide information that other
members might find useful and reliable. Social networks are trusted because of shared
experiences and the perception of shared values and shared needs. This phenomenon has
recently created and converted existing online communities into complex online social net-
works. Although the behavior of individuals in online networks can be slightly different from
the same individuals interacting in a more traditional social network (reality), it gives us
invaluable insights on the people we are communicating with, which groups are we engaged,
which are our preferences, etc.

1.2.1.2
Reality
Mining
To overcome the discrepancy between online and “offline” networks, reality mining
techniques can
be empowered to approximate both worlds, proving awareness about people actual behavior.
It typically analyzes sensor data (from mobiles, video cameras, satellites, etc) to extract
subtle patterns
that help to predict and understand future human behavior. These predictive patterns begin
with
biological “honest signals,” human behaviors that evolved from ancient primate signaling
mechanisms, and which are major factors in human decision making. In fact, these systems
enable us to have the “big picture” of specific social contexts by aggregating and averaging
the collected data (e.g., identify and prevent epidemics). Moreover, it allows data/events
correlation and consequently future occurrences extrapolation.

1.2.1.3 Context-
Awareness
In today’s services, the sought to deal with linking changes in the environment with
computer systems is becoming increasingly important, allowing computers to both sense and
react based on their environment. Additionally, devices may have information about the
circumstances under which they are able to operate and based on rules, or an intelligent
stimulus, react accordingly [15]. By assessing and analyzing visions and predictions on
computing, devices, infrastructures and human interaction, it becomes apparent that:
a. context is available, meaningful, and carries rich information in such environments,
b. that users’ expectations and user experience is directly related to context,
c. acquiring, representing, providing, and using context becomes a crucial enabling technology for
the vision of disappearing computers in everyday environments.
 1.2.2 Architectural Framework and Methodology

In order to enable human behavior understanding and prediction, there are several independent
but complementary steps that can be grouped into three different categories: Data Management, New
Knowledge Generation and Service Exposure and Control. Figure 1 depicts these relationships as
well as the sequence of activities involved.

1.2.2.1 Data Management

This activity usually starts with data acquisition. This process involves gathering
information from different information systems. In our experiments we included user preferences,
social networks, devices, policies, profiling algorithms, external

Fig. 1 Human Behavior Understanding and Prediction process

Fig. 2 Example of information to be stored in the Human Data Repository

contexts, as well as reasoned and predicted knowledge. Figure 2 exemplifies the type of information
 that can be stored in the Human Data Repository, a set of properties build within a generic structure
that allow services of the future to use user related information, while respecting their privacy, needs
and concerns.

1.2.2.2 Knowledge Generation

New information inference is based on user related data, which we call context and can be
separated into three different categories: real-time, historical data and reasoned context. Nevertheless,
only real-time information is considered as context in the real meaning of this term. As illustrated in
Fig. 20.3, there are several lay- ers of abstraction in a context-aware system and any context-aware
middleware or architecture must therefore be capable of building representations and models of these
abstractions. However, these high-level abstractions can only be made from lower level context, which
requires some form of context management function (performed by a Context Broker). In our case,
this is performed at the Human Data Repository.

Fig. 3 Context layering

model
1.2.2.3 Service Exposure and Control

The third layer is divided into two main capabilities. The first is user-centric and re- lates to the
ability of the user to stay in control of the whole scenario, enabling it to specify when, what, why,
who, where and how the data is or can be accessed. This opens the doors for opportunistic
communications, as user context is disclosed ac- cording to contextual privacy policies and
settings, enabling systems and devices to sense how, where and why information and content are
being accessed and respond accordingly.

1.2.2.4 Innovations

The analysis of the first results indicated the following key

findings:
• It is possible to infer user behavior based on user preferences, social networks and context- aware
systems, with the help of reality/data mining techniques.
• Proximity and Similarity are great weight indicators for inferring influence and
can be computed or calculated analytically.
• Both online and offline social networks have influence over a person’s
behavior.
• User perceived QoE is improved as the methodology delivers personalization, contextualization,
interactivity, adaptation and privacy.
• Users are willing to participate in their own profiling experience and the results are positive.

2.0 Managing Trust in Online Social Networks

 2.1 Introduction
Users of the online social networks may share their experiences and opinions within the
networks about an item which may be a product or service. The user faces the problem of evaluating
trust in a service or service provider before making a choice. Recommendations may be received
through a chain of friends network, so the problem for the user is to be able to evaluate various types
of trust opinions and recommendations. This opinion or recommendation has a great influence to
choose to use or enjoy the item by the other user of the community. Collaborative filtering system is
the most popular method in recommender system. The task in collaborative filtering is to predict the
utility of items to a particular user based on a database of user rates from a sample or population of
other users. Because of the different taste of different people, they rate differently according to their
subjective taste. If two people rate a set of items similarly, they share similar tastes. In the
recommender system, this information is used to recommend items that one participant likes, to other
persons in the same cluster.

Trust systems can in general be used to derive local and subjective measures of trust, meaning that
different agents can derive different trust in the same entity. Another characteristic of trust systems is
that they can analyze multiple hops of trust transitivity Reputation systems on the other hand normally
compute scores based on direct input from members in the community which is not based on
transitivity. Still there are systems that have characteristics of being both a reputation system and a
trust system.

2.2 Online Social

Network
Professor J. A. Barnes has introduced the term “Social Network” in 1967 to describe the
associations of people drawn together by family, work, hobby etc.; for emotional, instrumental,
appraisal and information support [10]. These networks may operate in many levels from family
level to a level of nations and can play important roles in communications among people,
organizations and even nations; as well as the way how problems are solved and how organizations
may run in better way.
The first online social networks were called UseNet Newsgroups (www.usenet. com) designed
and built by Duke University graduate students Tom Truscott and Jim Ellis in 1979. Since then the
online social networks have a continuous growth in size and numbers. In February 2010; online social
network giant Facebook cross the massive 370 million registered monthly active user. The Table 1
below shows a brief timeline of the history of online social networking.
4.1 Privacy in Online Social Networks
 There is a dramatic growth in number and popularity of online social networks. There
are many networks available with more than 100 million registered users such as
Facebook, MySpace, QZone, Windows Live Spaces etc.
 People may connect, discover and share by using these online social networks. The
exponential growth of online communities in the area of social networks attracts the
attention of the researchers about the importance of managing trust in online
environment.
 Users of the online social networks may share their experiences and opinions within the
networks about an item which may be a product or service.
 Collaborative filtering system is the most popular method in recommender system.
o The task is to predict the utility of items to a particular user based on a database
of user rates from a sample or population of other users.
 Because of the different taste of different people, they rate differently according to their
subjective taste.
 If two people rate a set of items similarly, they share similar tastes. In the recommender
system, this information is used to recommend items that one participant likes, to other
persons in the same cluster.
 Performs poor when there is insufficient previous common rating available between
users; known as cold start problem
  To overcome the cold start problem trust based approach to recommendation has
emerged.

 This approach assumes a trust network among users and makes recommendations based
on the ratings of the users that are directly or indirectly trusted by the target user.
 Trust could be used as supplementary or replacement of collaborative filtering system
 Trust and reputation systems can be used in order to assist users in predicting and
selecting the best quality services
 Binomial Bayesian reputation systems normally take ratings expressed in a discrete
binary form as either
o positive (e.g. good) or
o negative (e.g. bad).
 Multinomial Bayesian reputation systems allow the possibility of providing ratings with
discrete graded levels such as e.g. mediocre – bad –average – good – excellent
 Trust models based on subjective logic are directly compatible with Bayesian reputation
systems because a bi-jectivemapping exists between their respective trust and reputation
representations.
 This provides a powerful basis for combining trust and reputation systems for assessing
the quality of online services.
 Trust systems can be used to derive local and subjective measures of trust, meaning that
different agents can derive different trust in the same entity.
 Reputation systems compute scores based on direct input from members in the
community which is not based on transitivity
 Bayesian reputation systems are directly compatible with trust systems based on
subjective logic, they can be seamlessly integrated. This provides a powerful and
flexible basis for online trust and reputation management.
Online Social Networks
 A social network is a map of the relevant ties between the individuals, organizations,
nations etc. being studied.
 With the evolution of digital age, Internet provides a greater scope of implementing
social networks online. Online social networks have broader and easier coverage of
members worldwide to share information and resources.
 The first online social networks were called UseNet Newsgroups. designed and built by
Duke University graduate students Tom Truscott and Jim Ellis in 1979.

 Facebook is the largest and most popular online social network at this moment
 (www.insidefacebook.com).
 It had 350 million Monthly Active Users (MAU) at the beginning of January 2010. But
it has been growing too fast around the world since then.
 As on 10 February 2010, roughly 23 million more people are using Facebook compared
to 30 days ago, many in countries with big populations around the world. This is an
interesting shift from much of Facebook‟s international growth to date.
 Once Facebook began offering the service in multiple languages it started blowing up in
many countries like Canada, Iceland, Norway, South Africa, Chile, etc.
 The United States is at the top with more than five million new users; it also continues
to be the single largest country on Facebook, with 108 million MAU
 Table a Top ten mostly visited social networks in Jan‟09– based on MAU


4.2 Trust in Online Environment

 Trust has become important topic of research in many fields including
sociology, psychology, philosophy, economics, business, law and IT.
 Trust is a complex word with multiple dimensions.
 Though dozens of proposed definitions are available in the literature, a complete formal
unambiguous definition of trust is rare.
 Trust is used as a word or concept with no real definition.
 Trust is such a concept that crosses disciplines and also domains. The focus of definition
differs on the basis of the goal and the scope of the projects.
 Two forms
o reliability trust or evaluation trust
o decision trust
 Evaluation trust can be interpreted as the reliability of something or somebody. It can
be defined as the subjective probability by which an individual, A, expects that another
individual, B, performs a given action on which its welfare depends.
 The decision trust captures broader concept of trust. It can be defined as the extent to
which one party is willing to depend on something or somebody in a given situation
 with a feeling of relative security, even though negative consequences are possible.

Neo4j is a powerful, high-performance, open-source graph database that

enables the efficient management and querying of highly connected data.
Unlike traditional relational databases, Neo4j uses graph structures to
represent and store data, making it uniquely suited for applications involving
complex relationships and dynamic, interconnected data. As the world’s
leading graph database, Neo4j has become essential for organizations looking
to leverage the power of graph technology for a variety of use cases.
Neo4j is a powerful and flexible graph database management system,
designed to efficiently store and query highly interconnected data. Unlike
traditional relational databases, which store data in tables, Neo4j uses a graph
structure to represent and navigate relationships between data entities.
Neo4j structure
Neo4j stores and present the data in the form of graph not in tabular format or not in a
Json format. Here the whole data is represented by nodes and there you can create a
relationship between nodes. That means the whole database collection will look like a
graph, that’s why it is making it unique from other database management system.

MS Access, SQL server all the relational database management system use tables to
store or present the data with the help of column and row but Neo4j doesn’t use
tables, row or columns like old school style to store or present the data.
What is a Graph Database?
A graph database uses graph theory to store, map, and query relationships. It consists
of nodes, edges, and properties, where:
 Nodes represent entities such as people, businesses, or any data item.
 Edges (or relationships) connect nodes and illustrate how entities are related.
 Properties provide additional information about nodes and relationships.
This structure allows graph databases to model real-world scenarios more naturally
and intuitively than traditional relational databases.
Features of Neo4J
High Performance and Scalability
Neo4j is designed to handle massive amounts of data and complex queries quickly
and efficiently. Its native graph storage and processing engine ensure high
performance and scalability, even with billions of nodes and relationships.
Cypher Query Language
Neo4j uses Cypher, a powerful and expressive query language tailored for graph
databases. Cypher makes it easy to create, read, update, and delete data, allowing
users to perform complex queries with concise and readable syntax.
ACID Compliance
Neo4j ensures data integrity and reliability through ACID (Atomicity, Consistency,
Isolation, Durability) compliance. This guarantees that all database transactions are
processed reliably and ensures the consistency of the database even in the event of
failures.
Flexible Schema
Unlike traditional databases, Neo4j offers a flexible schema, allowing users to add or
modify data models without downtime. This adaptability makes it ideal for evolving
data structures and rapidly changing business requirements.
Neo4j Usage
If your Database Management System has so many interconnecting relationships then
you can use Neo4j that will be the best choice. Neo4j is highly preferable to store
data that contains multiple connections between nodes. This is where the Neo4j
comes in it’s more comfortable to use with relational data than the relational
database. Because Neo4j doesn’t require a predefined schema, you just need to load
the data here the data is the main structure. It is schema optional Database
Management System.
There are some unique features that will make you choose Neo4j over any other
Database Management System. Neo4j is surrounded by relationships but there is no
need to set up primary key or foreign key constraints to any data. Here you can add
any relation between any nodes you want. That makes the Neo4j extremely suited for
Networking data, below is the list of data areas where you can use this Database
Management System.
 Social network analysis like in Facebook, Twitter or in Instagram
 Network Diagram
 Fraud Detection
 Graph based searched of digital assets
 Data Management
 Real-time product recommendation
Advantages of Neo4j:
1. Representation of connected data is very easy.
2. Retrieval or traversal or navigation of connected data is very fast.
3. It uses simple and powerful data model.
4. It can represent semi-structured data is easy.
Disadvantages of Neo4j:
1. OLAP support for these types of databases is not well executed.
 2. In this area, still there are lots of research happening around.

Node
Nodes are used to represent entities (discrete objects) of a domain.
The simplest possible graph is a single node with no relationships. Consider the following graph,
consisting of a single node.

The example graph shown below introduces the basic concepts of the property graph:

CREATE (:Person:Actor {name: 'Tom Hanks', born: 1956})-[:ACTED_IN {roles: ['Forrest']}]->(:Movie

{title: 'Forrest Gump', released: 1994})<-[:DIRECTED]-(:Person {name: 'Robert Zemeckis', born: 1951})

The node labels are:

 Person
 Actor
The properties are:
 name: Tom Hanks
 born: 1956

The node can be created with Cypher using the query:

Syntax
CREATE (:Person:Actor {name: 'Tom Hanks', born: 1956})
Node labels
Labels shape the domain by grouping (classifying) nodes into sets where all nodes with a certain
label belong to the same set.
 For example, all nodes representing users could be labeled with the label User. With that in place,
you can ask Neo4j to perform operations only on your user nodes, such as finding all users with a
given name.
Since labels can be added and removed during runtime, they can also be used to mark temporary
states for nodes. A Suspended label could be used to denote bank accounts that are suspended, and
a Seasonal label can denote vegetables that are currently in season.
A node can have zero to many labels.
In the example graph, the node labels, Person, Actor, and Movie, are used to describe (classify) the
nodes. More labels can be added to express different dimensions of the data.
The following graph shows the use of multiple labels.

Relationship
A relationship describes how a connection between a source node and a target node are related. It
is possible for a node to have a relationship to itself.
A relationship:
 Connects a source node and a target node.
 Has a direction (one direction).
 Must have a type (one type) to define (classify) what type of relationship it is.
 Can have properties (key-value pairs), which further describe the relationship.
Relationships organize nodes into structures, allowing a graph to resemble a list, a tree, a map, or
a compound entity — any of which may be combined into yet more complex, richly inter-
connected structures.

The relationship type: ACTED_IN

The properties are:
 roles: ['Forrest']
 performance: 5
The roles property has an array value with a single item ('Forrest') in it.
The relationship can be created with Cypher using the query:
 CREATE ()-[:ACTED_IN {roles: ['Forrest'], performance: 5}]->()
Relationships always have a direction. However, the direction can be disregarded where it is not
useful. This means that there is no need to add duplicate relationships in the opposite direction
unless it is needed to describe the data model properly.
A node can have relationships to itself. To express that Tom Hanks KNOWS himself would be
expressed as:

Relationship type
A relationship must have exactly one relationship type.
Below is an ACTED_IN relationship, with the Tom Hanks node as the source node and Forrest
Gump as the target node.

Observe that the Tom Hanks node has an outgoing relationship, while the Forrest Gump node has
an incoming relationship.

Properties
Properties are key-value pairs that are used for storing data on nodes and relationships.
The value part of a property:
 Can hold different data types, such as number, string, or boolean.
 Can hold a homogeneous list (array) containing, for example, strings, numbers, or boolean values.
Example 1. Number

CREATE (:Example {a: 1, b: 3.14})

 The property a has the type integer with the value 1.
 The property b has the type float with the value 3.14.
Example 2. String and boolean
CREATE (:Example {c: 'This is an example string', d: true, e: false})
 The property c has the type string with the value 'This is an example string'.
 The property d has the type boolean with the value true.
 The property e has the type boolean with the value false.
Example 3. Lists
CREATE (:Example {f: [1, 2, 3], g: [2.71, 3.14], h: ['abc', 'example'], i: [true, true, false]})
 The property f contains an array with the value [1, 2, 3].
 The property g contains an array with the value [2.71, 3.14].
 The property h contains an array with the value ['abc', 'example'].
 The property i contains an array with the value [true, true, false].