Social Network Analysis – SNA

WHAT IT IS

The Social Network Analysis (SNA) is a research procedure that focuses on identifying and comparing the relationships within and between individuals, groups and systems in order to model the real world interactions at the heart of organizational knowledge and learning processes. Essentially, Social Network Analysis aims at illuminating informal relationships: ‘who knows whom’ and ‘who shares with whom’. This allows researchers to visualize and understand the diverse relationships that either facilitate or impede knowledge sharing.

HISTORY

The study of networks has quite old historical roots. Both network studies and “graph theory” which has an important role in the analysis of network structures owe their birth and initial development to a famous riddle. In 1736, Leonhard Euler who was an important mathematician became interested in a mathematical riddle called the “Königsberg Bridge Problem”. The city of Königsberg which is called Kaliningrad today and lies in Russia, was built on the banks of the Pregel River in that was then Prussia and on two islands that lie in midstream. There were seven bridges in Pregel River that connect the land masses. The question that has become quite popular in that time asked “Does there exist any single path that crosses all seven bridges exactly once each?”. So the problem is, by starting from the islands or any of the land masses in the shore, to pass each of these seven bridges only once without moving or flying around the terrestrial and to be able to come back to the starting point. According to the rumors, the people of Königsberg have spent fruitless hours to find whether such a path exists. Euler proved that there is not, by observing that since any such path must both enter and leave every vertex it passes through, except the first and last, there can at most be two vertices in the network with an odd number of edges attached. Euler formed the basis of “graph theory” by putting forth of the properties of the graphs which is today called “Eulerian Graph” while searching for the solution of that riddle. Euler proved the impossibility of this path’s existence by using a graph which is a mathematical object consisting of points, also called vertices or nodes; and lines, also called edges or links. Thus, this famous bridge problem has become a mathematical expression as the question of whether there exists any “Eulerian Path” on the network. An Eulerian path is precisely a path that traverses each edge exactly once. Many consider Euler’s proof to be the first theorem of graph theory which has become the principal mathematical language for describing the properties of networks and is now highly developed field of mathematics (Ceyhun, 1976: 78, Barabasi et.al., 2006: 1-2).

In its simplest form, a network consists of a set of discrete elements (vertices) and a set of connections (edges) that link the elements. These elements and their links can consist of many examples as computer and communication lines, people and their friendships or scientific publications and their citations and so on. This indicates the wide range usage area and power of graph theory. As a result, especially within the last decades, graph theory diverged from just being a mathematical theory and started to apply in other disciplines as computer sciences and engineering, but especially it gained a wide acceptance in sociology. (Kocak 2014: 1-2)

SOCIAL NETWORKS AND ITS ANALYSIS

Social network analysis has a long history and connection to the study of organizations and businesses. Early social network research was built on manually collected and analyzed data about social ties. Since 1950’s, there has been an increasing interest for quantitative methods in sociology and anthropology, thus social scientists started to interest in mathematical language of graph theory in terms of examining the data obtained from ethnographic studies. A large part of the terminology that used in social network analysis has taken or adapted directly from graph theory. In similar, the structural properties and links of networks provide a useful tool for explaining the diffusion and impacts as well, like a possible diffusion of an epidemic or a global information transfer. Social network can be defined as a set of people -actor-, and the links and interactions between these actors. Nodes are the individual actors in a network; links are the relations between these actors. On the other hand, social network analysis can be expressed as examining the structure of social networks with the concepts of graph theory. In the center of network analysis, there are some key concepts which are fundamental for the discussion of social network. Some of these concepts are actor, relational tie, dyad, triad and subgroup. The social entities are referred as the concept of “actor”. These actors can be discrete individual, corporate or collective social units. Individuals in a group, departments within a corporate or nation-states in the world system can be the examples of the concept of “actor”. Most of social network applications focus on the same type of actor collections as people in a work group. These kinds of collections are called as one-mode network. Actors are linked to one another by social ties which can be handled as relational tie. A tie establishes a linkage between a pair of actors. The most common examples of ties can be expressed as behavioral interactions like talking together-sending messages, biological relationships like kinship, evaluation of one person by another like expressed friendship, liking, respect and transfers of material resources like business transactions etc. A relationship establishes a tie between two actors at the most basic level. So this tie is a property of the pair and it cannot be handled as a property of just an individual actor. Hence, a dyad consists of a pair of actors and the ties between them. Dyads are defined as the most basic units in the statistical analysis of social networks. On the other a triad is defined as a subset of three actors and the ties among them. A subgroup which is another concept in social network is defined as any subset of actors and all ties among them (Wasserman and Faust, 1994:17-19).

ONLINE SOCIAL NETWORKS

Internet and web are defined as a huge network which consist of connected computers, connected web sites or connected users (Scharnhorst, 2003). Therefore, the new developments in Internet caused the online restructuring of a huge social network and the properties of this new structure became the field of interest of many researchers. The rapidly growing popularity of social networks has let the sociologists and computer scientists to examine the properties of these networks. Based on previous knowledge it can be said that online social networks are consist of the actors and the links between these actors just like the other social networks. So, online social networks can also be analyzed by using the methods and concepts in graph theory and social network analysis.

THE PROCESS OF SOCIAL NETWORK ANALYSIS

A quick look at Social Network Analysis

The Social Network Analysis involves:

·        Collecting information about relationships within a defined group or network of people.

 – Identifying the target network (e.g. team, group, department).

 – Collecting data by interviewing managers and key players regarding specific needs and problems.

 – Outlining and clarifying objectives and the scope of analysis

 – Determining the level of reporting required.

 – Formulating hypotheses and questions.

– Developing a survey methodology and the questionnaire.

– Interviewing individuals in the network to identify relationships and knowledge flows.

·        Mapping out the network visually: mapping responses either manually or by using a software tool designed for the purpose.

·        Generating a baseline through the analysis of data from the survey responses.

·        Using this baseline for planning and prioritizing changes and interventions to improve social connections and knowledge flows within the group or network.

·        Designing and implementing actions to bring about

·        Mapping the network again after an appropriate period

(source; www.library.nhs.uk/knowledgemanagement)

Why Social Network Analysis?

SUMMARY

In general, the popularity and the importance of social networks are increasing continuously because of the developments in information technologies’ which extensively moves every day’s life. In this context, to put forward all of the structural features of a social networks by using methods of social network analysis gain importance in terms of being able to create better understanding about a networks.

“The social network analysis means to analyze a social network by using the concepts of graph theory – concepts as degree, component, clique, path, etc. which are used to examine graph structures find their natural equivalents in social networks as well and they transform social network analysis to an objective method. It is seen that concepts of graph theory as degree distribution or the largest connected component which gradually became more refined are successfully applied to even quite large networks as Facebook, etc.” (Kocak 2014, 134)

At the conclusion of this brief blog covering the topic of Social Network Analysis it will be easy to figure out that value of comprehensive Social Network Analysis is substantially increasing in future. There are no estimates available covering period from now to forthcoming decades up to year 2040, however experts agree that by then, use of social media will be omnipresent and integrated into our daily lives in many ways. In this scenario challenge will be how to manage with the massive amounts of data what will overwhelm the masses.

 

Social Network Analysis – SNA

WHAT IT IS

The Social Network Analysis (SNA) is a research procedure that focuses on identifying and comparing the relationships within and between individuals, groups and systems in order to model the real world interactions at the heart of organizational knowledge and learning processes. Essentially, Social Network Analysis aims at illuminating informal relationships: ‘who knows whom’ and ‘who shares with whom’. This allows researchers to visualize and understand the diverse relationships that either facilitate or impede knowledge sharing.

HISTORY

The study of networks has quite old historical roots. Both network studies and “graph theory” which has an important role in the analysis of network structures owe their birth and initial development to a famous riddle. In 1736, Leonhard Euler who was an important mathematician became interested in a mathematical riddle called the “Königsberg Bridge Problem”. The city of Königsberg which is called Kaliningrad today and lies in Russia, was built on the banks of the Pregel River in that was then Prussia and on two islands that lie in midstream. There were seven bridges in Pregel River that connect the land masses. The question that has become quite popular in that time asked “Does there exist any single path that crosses all seven bridges exactly once each?”. So the problem is, by starting from the islands or any of the land masses in the shore, to pass each of these seven bridges only once without moving or flying around the terrestrial and to be able to come back to the starting point. According to the rumors, the people of Königsberg have spent fruitless hours to find whether such a path exists. Euler proved that there is not, by observing that since any such path must both enter and leave every vertex it passes through, except the first and last, there can at most be two vertices in the network with an odd number of edges attached. Euler formed the basis of “graph theory” by putting forth of the properties of the graphs which is today called “Eulerian Graph” while searching for the solution of that riddle. Euler proved the impossibility of this path’s existence by using a graph which is a mathematical object consisting of points, also called vertices or nodes; and lines, also called edges or links. Thus, this famous bridge problem has become a mathematical expression as the question of whether there exists any “Eulerian Path” on the network. An Eulerian path is precisely a path that traverses each edge exactly once. Many consider Euler’s proof to be the first theorem of graph theory which has become the principal mathematical language for describing the properties of networks and is now highly developed field of mathematics (Ceyhun, 1976: 78, Barabasi et.al., 2006: 1-2).

In its simplest form, a network consists of a set of discrete elements (vertices) and a set of connections (edges) that link the elements. These elements and their links can consist of many examples as computer and communication lines, people and their friendships or scientific publications and their citations and so on. This indicates the wide range usage area and power of graph theory. As a result, especially within the last decades, graph theory diverged from just being a mathematical theory and started to apply in other disciplines as computer sciences and engineering, but especially it gained a wide acceptance in sociology. (Kocak 2014: 1-2)

SOCIAL NETWORKS AND ITS ANALYSIS

Social network analysis has a long history and connection to the study of organizations and businesses. Early social network research was built on manually collected and analyzed data about social ties. Since 1950’s, there has been an increasing interest for quantitative methods in sociology and anthropology, thus social scientists started to interest in mathematical language of graph theory in terms of examining the data obtained from ethnographic studies. A large part of the terminology that used in social network analysis has taken or adapted directly from graph theory. In similar, the structural properties and links of networks provide a useful tool for explaining the diffusion and impacts as well, like a possible diffusion of an epidemic or a global information transfer. Social network can be defined as a set of people -actor-, and the links and interactions between these actors. Nodes are the individual actors in a network; links are the relations between these actors. On the other hand, social network analysis can be expressed as examining the structure of social networks with the concepts of graph theory. In the center of network analysis, there are some key concepts which are fundamental for the discussion of social network. Some of these concepts are actor, relational tie, dyad, triad and subgroup. The social entities are referred as the concept of “actor”. These actors can be discrete individual, corporate or collective social units. Individuals in a group, departments within a corporate or nation-states in the world system can be the examples of the concept of “actor”. Most of social network applications focus on the same type of actor collections as people in a work group. These kinds of collections are called as one-mode network. Actors are linked to one another by social ties which can be handled as relational tie. A tie establishes a linkage between a pair of actors. The most common examples of ties can be expressed as behavioral interactions like talking together-sending messages, biological relationships like kinship, evaluation of one person by another like expressed friendship, liking, respect and transfers of material resources like business transactions etc. A relationship establishes a tie between two actors at the most basic level. So this tie is a property of the pair and it cannot be handled as a property of just an individual actor. Hence, a dyad consists of a pair of actors and the ties between them. Dyads are defined as the most basic units in the statistical analysis of social networks. On the other a triad is defined as a subset of three actors and the ties among them. A subgroup which is another concept in social network is defined as any subset of actors and all ties among them (Wasserman and Faust, 1994:17-19).

ONLINE SOCIAL NETWORKS

Internet and web are defined as a huge network which consist of connected computers, connected web sites or connected users (Scharnhorst, 2003). Therefore, the new developments in Internet caused the online restructuring of a huge social network and the properties of this new structure became the field of interest of many researchers. The rapidly growing popularity of social networks has let the sociologists and computer scientists to examine the properties of these networks. Based on previous knowledge it can be said that online social networks are consist of the actors and the links between these actors just like the other social networks. So, online social networks can also be analyzed by using the methods and concepts in graph theory and social network analysis.

THE PROCESS OF SOCIAL NETWORK ANALYSIS

A quick look at Social Network Analysis

The Social Network Analysis involves:

·        Collecting information about relationships within a defined group or network of people.

 – Identifying the target network (e.g. team, group, department).

 – Collecting data by interviewing managers and key players regarding specific needs and problems.

 – Outlining and clarifying objectives and the scope of analysis

 – Determining the level of reporting required.

 – Formulating hypotheses and questions.

– Developing a survey methodology and the questionnaire.

– Interviewing individuals in the network to identify relationships and knowledge flows.

·        Mapping out the network visually: mapping responses either manually or by using a software tool designed for the purpose.

·        Generating a baseline through the analysis of data from the survey responses.

·        Using this baseline for planning and prioritizing changes and interventions to improve social connections and knowledge flows within the group or network.

·        Designing and implementing actions to bring about

·        Mapping the network again after an appropriate period

(source; www.library.nhs.uk/knowledgemanagement)

Why Social Network Analysis?

SUMMARY

In general, the popularity and the importance of social networks are increasing continuously because of the developments in information technologies’ which extensively moves every day’s life. In this context, to put forward all of the structural features of a social networks by using methods of social network analysis gain importance in terms of being able to create better understanding about a networks.

“The social network analysis means to analyze a social network by using the concepts of graph theory – concepts as degree, component, clique, path, etc. which are used to examine graph structures find their natural equivalents in social networks as well and they transform social network analysis to an objective method. It is seen that concepts of graph theory as degree distribution or the largest connected component which gradually became more refined are successfully applied to even quite large networks as Facebook, etc.” (Kocak 2014, 134)

At the conclusion of this brief blog covering the topic of Social Network Analysis it will be easy to figure out that value of comprehensive Social Network Analysis is substantially increasing in future. There are no estimates available covering period from now to forthcoming decades up to year 2040, however experts agree that by then, use of social media will be omnipresent and integrated into our daily lives in many ways. In this scenario challenge will be how to manage with the massive amounts of data what will overwhelm the masses.

 

My Data

Companies are gathering information of our shopping behavior and other personal data. But what My Data actually is and what it is used for? In this blog text I try to understand the definition behind My Data, the reasons why companies want to gather data from their customers and how are they going to profit by doing that.

My Data, a term created in Great Britain, is based on data that have been collected from users of different applications and services. It provides the individuals easy access to the data gathered from them and one of the main points in My Data is that individuals can manage that information. This issue is also strongly connected to privacy of individuals and that’s why EU has started to prepare new directives to protect individual privacy. (Poikola et al. 2014; Aalto-Setälä 2016.)

My Data is consisting of our own personal data. Personal data is seen as a resource in which the individual him-/herself can or cannot have control and access to. Our personal data is formed of information that is stored in private and governmental organizations database. These organizations have information about our health, retail purchases, banking and finance services, used web services and our habits of communication and the use of different medias. (Poikola et al.)

Personal data is mostly in a digital form. Different digital technologies are gathering information from our daily activities, social relations and relationships. This type of information is transferred between many different sites. (Lupton 2016.)

figure1-1

Sources of personal data (Poikola etc.)

What then makes personal data to My Data? As a minimum requirement can be defined the access and control to your personal data. Furthermore, My Data gives the possibility to sell our personal data to third parties, manage the personal information found from us, e.g. remove or correct our personal information. Also it enables us to see the real content of the personal information gathered from us. My Data is individual’s way of benefiting of the personal data. (Poikola et al.)

My Data approach is created to protect our human rights and at the same time help companies to have data. The reason for this kind of approach is that individuals could have possibility to manage the collected data. (Poikola et al.)

When looking into the world of data, there is often mentioned term big data. Big data means that the data is collected either from digital or traditional sources and it is basically non-classified mass of data. It is based on interaction and it leads to transaction. (Arthur 2014, 46; Kolehmainen 2011.) The classification of the information differs big data from My Data.

This YouTube video considers the future and the value of the personal data that can be transferred to My Data. Stuart Lacey is presenting how our own personal data collected from different applications, e.g. Facebook, can be sold to companies to used in their marketing campaigns for example. As Poikola et al. in their paper of My Data also Lacey discuss how we can ourselves benefit from our personal data as an asset in the field of business.

https://www.youtube.com/watch?v=JIo-V0beaBw

Issues concerning my data were widely discussed in Finnish media in summer 2016. One of the biggest retail chains in Finland, S-Ryhmä, announced that it is going to start gathering more precise data from its member’s retail purchases. The data of individual’s purchases is collected when the customer is using his or her bonus card. Previously S-Ryhmä has gathered data from its customer’s consumption habits only in level of different product groups. In this new practice, all purchases are individually and detailed reported to S-Ryhmä. (Koivisto 2016.)

S-Ryhmä reports in its own website that the data gathered from its customers are used to provide customers more targeted advertising, developing company’s business and furthermore, developing services for customers using by the data collected from their retail purchases (S-kanava). Currently S-Ryhmä has not announced any specific information to what kind of services its customer’s data is used. According to SOK’s customer business manager Pekka Malmirae new and better products are provided customers during the year 2016. (Koivisto 2016.) Data from retail purchases can also be used to report if there are any issues of product safety. If customers have bought a product that has to be returned to the shop, they can be easily contacted because of the existing data files. (Haapanen 2016.)

The reason why this change to S-Ryhmä’s data collection caused so much publicity was that people feel their privacy is threatened. What if the data gathered is hacked? And do customers really benefit from the services that are created by using their personal data? (Koivisto 2016.)

Due to the wide reporting and statements from different authorities S-Ryhmä decided to make slight changes to this new data collection system. It is providing to its customers the possibility to choose where the gathered data can be used. Data is still collected but customer can deny the usage of personal data for example to targeted marketing. (Haapanen 2016.) 23838550-730x309

The variety of Finnish retail chain membercards (Kuivaniemi 2016)

Another retail chain in Finland, K-Ryhmä, has been gathering personal data from detailed retail purchases for couple of years now. The difference between S- and K-ryhmä was that K-Ryhmä’s members have the possibility to choose how much data company receives. Consumers can either give only the total amount of their purchases or detailed information what they have been buying. Still, less than one percent of the members of K-ryhmä have denied collecting detailed data from their purchases. (Ryynänen 2016.)

What are the benefits of using my data? Companies can target their product selection to match needs of costumers and at the same time reduce loss by being able to estimate the amount of different product consumption. From customers point of view they can receive tailored services and discounts from their purchases. (Halminen 2016.)

It is important to consider pro’s and con’s when discussing the privacy of individual’s. Companies have to take care of their data protection and individuals should consider how they could make My Data as their own business and how they can benefit from it. After all, both sides should benefit from My Data.

 

 

REFERENCES

Aalto-Setälä, Minna (2016) EU:n tietosuoja-asetus tulee – valmistaudu ajoissa. http://kauppakamari.fi/2016/03/31/eun-tietosuoja-asetus-tulee-valmistaudu-ajoissa/, referred 17.10.2016.

Arthur, Lisa (2014) Big Data Marketing: Engage Your Customers More Effectively and Drive Value. Hoboken, New Jersey.

Haapanen, Liisa (2016) S-ryhmä taipui: Asiakas voi sittenkin päättää asiakastietojen käytöstä. http://yle.fi/uutiset/3-9106003, referred 17.10.2016

Halminen, Laura (2016) Bonuskortti tallentaa kohta kaikki ostoksesi – HS selvitti, mitä hyötyä ja haittaa siitä on. http://www.hs.fi/talous/a1469763340034, referred 17.10.2016.

Koivisto, Matti (2016) S-ryhmä alkaa kerätä tarkempaa tietoa asiakkaista – Kuluttajaliitto tyrmistyi: “Nyt mennään pitkälle yksityiselämän asioihin”. http://yle.fi/uutiset/3-9055737, referred 17.10.2016.

Kolehmainen, Aleksi (2011) Mitä eroa on big datalla ja perinteisellä datalla? http://www.tivi.fi/CIO/2011-11-18/Mit%C3%A4-eroa-on-big-datalla-ja-perinteisell%C3%A4-datalla-3188167.html, referred 17.10.2016.

Kuivaniemi, Olli (2016) S-ryhmä pohtii, voiko bonuskortin käyttäjä kieltää tarkkojen tietojen keräämisen omista ostoksistaan. http://www.aamulehti.fi/kotimaa/s-ryhma-pohtii-voiko-bonuskortin-kayttaja-kieltaa-tarkkojen-tietojen-keraamisen-omista-ostoksistaan/, referred 17.10.2016.

Lupton, Deborah (2016) The Quantified Self. Wiley. Available as an e-book.

Poikola, Antti – Laine, Markus Petteri – Kuikkaniemi, Kai (2014) Ihmiskeskeinen vai yrityskeskeinen ratkaisu henkilökohtaisen datan hyödyntämiseen? http://fi.okfn.org/wg/my-data/, referred 16.10.2016.

Poikola, Antti – Kuikkaniemi, Kai – Honko, Harri. My Data – A Nordic Model for human-centered personal data management and processing. https://www.lvm.fi/documents/20181/859937/MyData-nordic-model/2e9b4eb0-68d7-463b-9460-821493449a63?version=1.0, referred 14.10.2016.

Ryynänen, Riitta (2016) K-ryhmä on kerännyt tietoja asiakkaiden ostoista jo vuosia. http://www.maaseuduntulevaisuus.fi/talous/k-ryhm%C3%A4-on-ker%C3%A4nnyt-tietoja-asiakkaiden-ostoista-jo-vuosia-1.157965, referred 17.10.2016.

S-kanava. Miten asiakastietoihin voidaan yhdistää ostotietoja? https://www.s-kanava.fi/web/s/kysymys?faq=169841_10810, referred 17.10.2016.

The social big data

Social medias do not get money by selling advertisement, one of the big revenue they get is from selling data.

Let’s get back in the early 2000s. Thanks to the development of the first chatrooms and the spread of television into nearly 80% of teenagers room, the fashion trends has accelerate, and this has complicated the work of designers and marketers. Their products lifecycle was getting shorter and shorter and they needed to always know what is the actual fashion.

That is why some companies decided to buy information directly beside the teenagers. Groups of 5 to 15 teenagers were gathered together in a room were they were interrogated by a marketers towards which artists they follow, which brand is fashionable or not and so on. Kids were paid up to 100$ a day !

telechargement-1

But today this is not happening anymore, and it is easily understandable, nowadays companies just have to contact Facebook, Twitter or Google and buy a bundle of customers data for nearly nothing and they have their answers. Some information are even free : You want to know if an artist is trendy ?Just go check his amount of followers and you’ll have the answer !

There is three types of data that can be sold by social medias :

The volunteered data, it is basicallyclip_image002_thumb-1 what was created on internet by the individuals on purpose, for instance a tweet, a like, a share.

The observed data, recorded data without you having purpose in it, for instance location.

The inferred data, which is a combination of the two others already treated and which is ready to use for brands and companies.

The fact that social media is making money with our data can be difficult to accept. Some people react saying that it is the price to pay for using a free tool, others react saying it’s not fair and decide to not use social media at all. But other people said « If social can make money with my data, why could not I make money too ? ». That is how a dutch student decided to sell his own data to a company for about 250$. He is proud of his because social media usually get 0.5$ per persons when selling informations, but the price to pay is bigger because the company had access to all oh his personal informations, even the private ones. But this king of cases are really rare because companies are not interested in one example of individual consumer but in an average, it means that they are more interested in buying 1000 no complete profiles instead of 5 complete ones.

The Targeted Advertising

Today the place of social media in our daily life is taking more and more space and significance. According to the business insider, the average internet user spend 2 and a half hours daily on social media. The amount of interactions on social media (likes on Facebook, +1 on google, or retweet on tweeter) is now huge and their treatment come now under big data.

One of the capture-decran-2016-10-11-a-10-35-23most important use of your personal data is targeted advertising. Don’t be surprised if the sponsored posts you see on Facebook is related on your Facebook’s pages likes or even with the websites you visited. Actually social media in not the first media that use targeted advertising. We could already see that before on broadcast media, especially on Television. If you watch the TV on a business channel you may see some airplanes companies advertising while when you watch more popular channel you may see more advertising about which is the cheapest grocery store. Mcapture-decran-2016-10-11-a-10-31-39oreover it you watch at the same channel at 8 am you, during the cartoon time you may see toys advertisements whereas if you look at the same channel at 3 pm you may more find stairlift advertisements. The fact is that considered the price of a TV advertising, companies wants to ensure that their advertising is not directed towards the wrong people. So it is why you don’t see the same advertisement on the morning and on the afternoon, as well as on the business channel and the popular channel.

But now, targeted advertising is even more used. Thanks to all the information we leave on the different social media, websites and even in our internet browser, companies can know what we like, what we do, what we buy and so on. Thanks to social media, marketers can know if we would be interested or not in their product and so they can decide whether they want to show us their advertisement or not. The more people they want to reach, the more they pay but, which is obvious, but they still can have a precise targeted advertisement and so save lots of money.

targeting_in_ad_system

 

You can see on the picture above that only two country are selected, but if the company decide to increase this number, the price will also rise. Some of the social media can also directly ask to their customer what advertising they want to see, in order to maybe make the customer feel like he still have a control of the content he watch on internet which is more or less just an illusion.

 

capture-decran-2016-10-11-a-10-39-49

Translation : “We want the advertisements that you see to be useful . tell us if you are interested in those subjects.”

 

 

 

 

 

Sentiment Analysis

What is the sentiment analysis all about?

In a nutshell:

nayttokuva-2016-10-17-kello-19-42-07
Pujari (2013)

From the image above you will find the philosophy of the sentiment analysis. What follows then in the blog, is the more detailed basis of the sentiment analysis, technology and most important – how it is utilized in social media.

The basics
Sentiment analysis is in recent year discovered way of learning more about customer behavior. Increase of social media, the companies have understood that their clientele is out there in the internet sharing their reviews. Sentiment means person’s emotion towards something, sentiment is derived from feeling rather than reason. Through the emotion under the written text, sentiment analysis can discover attitude, opinions and mood of the writer. (Heires 2015)

twins-amazon-reviewThe sentiment analyze apps evaluate whether the text is positive, negative or neutral. First the analysis were made manually, but now it is automated with the help of technology and analysts. There have been also developments in the text analytic tools that help to receive accurate information. (Heires 2015) Identifying the text either positive or negative is called categorization. Automated sentiment categorization has been utilized for example in product or movie reviews and preview of election result. (Khoo etc. 2012)

Would it be difficult to evaluate the sentiment of this review on the above?

Critic
The sentiment categorization within computer and information scientists have been claimed to be too straightforward. Social and communication researchers have been proposing that in sentiment analysis should be taken more factors into account. Within social and communication experts the focus is more in the polarity of positive and negative sentiments. There should be more frameworks that covers also the linguistic, social and psychologic sides of the analysis. (Khoo et al. 2012)

The problem of course is, that no app or computer think like human brain, so it is challenging to integrate emotion nuances to sentiment analysis. That is why sentiment analysis results have been accused to be too “black and white”. Human brains can’t be automated so in order to create efficiency, the meter must be quite simplistic. (Khoo et al. 2012)

Where would you need sentiment analysis?
Increase of social media has been activated customers to share their opinions. With online reviews, many people evaluate whether to purchase or not by other’s reviews. With the customer-centrichelp of those reviews in social media, companies can learn about their customers and modify their product towards more attractive. By knowing the clientele, companies will have great competitive advantage. In order to do so, companies need also to be aware of their competitors and constantly collect information about theirs’ products and reviews. (He et al 2016.)

Social media
Social media tools give companies countable opportunities to create business. With social media, customers and companies can communicate like never before. Companies have understood the power of social media – and the power of the customers. It is usual, that customers compare the servicescape and share their opinions in social media. It is important that companies develop their social analytics skill in order to quickly respond to customers’ demands. In this environment nowadays, companies need to be able to change their strategies rapidly. (He et al. 2016.)

In social media, sentiment analyse is an automated technique of tracking positive, negative and neutral emotions among customers. With the use of sentiment analysis, companies can collect widely customers or users emotions. Even though the sentiment analysis are being accused for being too simplistic, it gives you quickly information of large groups and the accuracy is good enough. (He et al. 2016.) The biggest social media sites Facebook, Twitter and Youtube have created applications for tracking down data. In recent years, also other operators have launched these sentiment analysis apps such as IBM social media capture. (Avery & Narayanan 2015.)

twitter_cover

Especially sentiment analysis in Twitter has been interested companies. For automated applications, Twitter is easy to analyze due to the limited amount of characters. The short tweets simplify the meaning and people tend to write only the main point. The tweets are also available for everybody, unlike in Facebook. (Avery & Narayanan 2015.) There are almost  boundless quantity of tweets in Twitter, every SECOND 6000 tweets are tweeted! That gives 500 million tweets per each day. After the first year of Twitter, year 2007, the quantity of tweets per day was 5000. (Internet live stats 2016) This crazy amount of online information about the customers is now being utilized.

To analyze sentiment, there are four dimensions used in general:
1) keyword spotting
2) lexical affinity
3) statistical methods
4) consept-based techniques. (Avery & Narayanan 2015.)

Let’s take the keyword spotting as an example. The analysts come up with 20 negative emotion keywords – including for example anger, confusion and depression. Then the analysts decide 20 positive emotion keywords – including for example happy, great and kind.  After that, these words are filtered through large amount of tweets. A database program goes through a large number of tweets and analyze whether the tweet contains positive or negative keyword. The app classified the tweets into positive – negative – or neutral (=don’t have any of the positive or negative keywords given).  The problem with this keyword spotting is, that algorithm cannot identify all the words.

“This morning was great.” or “This morning wasn’t great at all.”

That is why using different approaches aka dimensions, is the most accurate way for collecting information. (Avery & Narayanan 2015.)

Sentiment Analysis of Social Media texts lecture on Youtube:

Näyttökuva 2016-10-18 kello 15.24.59.png

Click the image to watch Sentiment Analysis of Social Media Text on Youtube. Link is also here. (Mohammad & Zhu 2014.)

REFERENCES:

Avery, Heather; Narayanan N.H. 2015. Sentiment Analysis Solutions for Insurance Business Decision Support. Industrial and Systems Engineering Conference. Proceedings. (2015): 527-535. Referred 18.10.2016 <http://search.proquest.com.ezproxy.utu.fi:2048/abicomplete/docview/1791989232/fulltextPDF/D7B153DEC91140A6PQ/13?accountid=14774&gt;

Heires, Katherine. Risk Management 62.10. Sentiment Analysis: Are You Feeling Risky? (Dec 2015): 14-15. Referred 12.10.2016 <http://search.proquest.com.ezproxy.utu.fi:2048/abicomplete/docview/1747316076/fulltextPDF/F56CE9100C7844E7PQ/8?accountid=14774&gt;

He, Wu; Tian, Xin; Chen, Yong; Chong, Dazhi. The Journal of Computer Information Systems56.2. Actionable social media competitive analytics for understanding customer experiences. (Winter 2016): 145-155. Referred 18.10.2016 <http://search.proquest.com.ezproxy.utu.fi:2048/abicomplete/docview/1795622769/fulltextPDF/53CC343DF50A4328PQ/8?accountid=14774&gt;

Internet Live Stats. 2016. Twitter statistics. Referred 18.10.2016 <http://www.internetlivestats.com/twitter-statistics/&gt;

Khoo, Christopher Soo-Guan; Nourbakhsh, Armineh; Jin-Cheon, Na. Online information Review 36.6. Sentiment analysis of online news text: a case study of appraisal theory. (2012): 858-878. Referred 13.10.2016 <http://search.proquest.com.ezproxy.utu.fi:2048/abicomplete/docview/1193817321/fulltextPDF/A8CEE7233CAD485FPQ/3?accountid=14774&gt;

Mohammad, Saif, M.; Zhu, Xiaodan. 2014. Sentiment Analysis of Social Media Texts. Youtube. Referred 18.10.2016 <https://www.youtube.com/watch?v=zv16Xyph7Ss&gt;

IMAGES:

Pujari, Pradeep. 2013. Slideshare Simple Sentiment Analysis Using Solr. Sentiment Analysis Innovation Summit. Slideshare. Referred 17.10.2016 <http://www.slideshare.net/PradeepPujari/sais-20431863&gt;

Pophangover. 2014. Referred 17.10.2016
<http://www.pophangover.com/44206/amazon-movie-reviews-twitter/&gt;

Sloan, Anjelica. 2014. Courting your customer. Referred 18.10.2016 <https://blogs.oracle.com/marketingcloud/courting-customer-relationship-advice-marketers&gt;

Zuhora, T. Fatima. 2016. 5+ Best Twitter Extension for Joomla. Themexpert blog. Referred 18.10.2016 <https://www.themexpert.com/blog/best-twitter-extension-for-joomla&gt;