– by ORKASH Labs, Copyright: ORKASH Services Pvt Ltd

Social media is the new buzz word in the marketing world. It has given an unprecedented level of voice to customers and potential customers, and as a result can provide companies with deep insights regarding customer views, opinions, sentiments, behavior and buying trends. By listening to social media and mining social media, it is possible to create market, customer and competitive intelligence of unparalleled accuracy and quality.

In recent times, the prime example of harnessing the social media for competitive advantage was demonstrated by the re-election of President Barack Obama in Nov 2012. His campaign had a specialist data analytics team that helped Obama refine the process of targeting TV ads and created detailed models of swing-state voters that could be used to increase the effectiveness of each campaign tool, from phone calls and door knocks, to direct mailings and most importantly, social media. No wonder, even as the Presidential race tightened in the closing weeks, President Obama maintained a substantial lead in both Facebook ‘likes’ and Twitter followers over Governor Romney. By the end of the campaign, Obama had 22.7 million followers and 32.2 million likes, compared to Romney’s 1.8 million followers and 12.1 million likes. In sum, the online behavioral data of American voters was co-related with their offline political identity and beliefs, using social media and data sciences, to a devastating effect. Clearly, a better harnessing of social media was one of the key differentiators, which resulted in Obama’s victory over Mitt Romney.

The Indian Context

Insofar as India is concerned, the impact of social media on the Indian political scene was examined in a previous Orkash blog post. Despite low internet penetration rates, social media is emerging as the single most powerful channel in India that is influencing a host of perceptions, from political sentiment, civil society led activism to consumer behavior. Another trend that is very visible is that internet penetration is rapidly spreading amongst the mobile phone users, a population that had grown to nearly a billion by end 2012, from just 45 million in 2002. Mobile phones based social media networks is the dominant format that is going to be prevalent in India. Key sectors in India where the data analytics of social media will impact business are the ‘Business to Consumer’ brands, for example financial and insurance instruments, consumer durables, entertainment industry, hospitality sector, electronic gadgets, retail, wellness and healthcare etc.

Social Media Intelligence “The Ultimate” Tool

Information that companies need for marketing and to meet competitive challenges is moving quickly from published and proprietary sources to the open, chaotic world of social media platforms.

Social media is rapidly changing the buying behaviour of customers. Individuals are increasingly expressing viewpoints on products, brands and services, seeking opinions online, commenting and comparing purchase options. Key influencers in such communities drive opinions and garner sentiments, in turn impacting purchase decisions. Concurrently, stray thoughts travel across the world in seconds, causing upheavals. Social media intelligence thus accords insights into the means to influence decision making.

The above screenshot of ORKASH technology identifies various Facebook users who have “Liked” the Honda page and commented on Honda . This also helps identify the influencer in this user network and clicking on a user id provides user details ( name, age group, gender etc. ) . The viewpoints through the users posts and status updates can be captured and a simultaneous analysis can be done on the influence this user has by capturing follow-up comments, “likes” received and the sentiments of the follow up comments.

At the organizational level, companies need to become hunters of information rather than gatherers. At the same time, companies would also need to mitigate impacts of competitors “hunting” them in social spaces, by making their employees/ team members aware of how easy it is to inadvertently divulge valuable information. Companies can also fall easy prey to mishandling of a complaint or dissatisfaction expressed by a consumer on social media, with severe repercussions for brand reputation and goodwill.

Socia media intelligence is a mission that should extend across the length and breadth of companies, particualrly those with BtoC products and services. Social media based intelligence will sharpen strategic insights and may help pre-empt key actions of competitors or lead to adjustments of marketing strategy. Navigating this new environment effectively requires new skills and technologies that can produce analytics and useful intelligence from vast amounts of unstructured data that is being generated daily on social media sites.

How Companies are using Social Media

Brand Reputation

As a case in point, Honda Motor Company has been using social networking sites to enhance its brand reputation. It is on all the major social networking sites like Facebook, Twitter, YouTube, Flickr, Pinterest, etc. Honda’s social media strategy is based around supporting business and corporate goals such as new product launches, corporate communications, public relations messages, tackling rumors, engaging with customers and communities like fans/ racing community and more. Honda is effectively using the social networking sites to keep track of conversations about the company, deliver key messages about their corporate social responsibility efforts, innovating new technologies, and also build relationships with journalists and bloggers.

Marketing and Sales

Many corporates are using social media to promote brands and products and to connect users to the company’s home pages. To a certain extent, they also use them to generate leads and even to help make sales. Most importantly, they use it to listen to what their customers are telling them about the products and their experiences with the company and its products.
Specifically, social media marketing is currently being used by organizations to:

  • Increase traffic to a website
  • Create buzz about a company or it’s product.
  • Learn what customers and fans want, their opinions, and consumer experience
  • Generate sales leads

When they begin implementing a social media marketing initiative, many companies
discover that they save money. After all, an account on Facebook or Twitter is free,
so it shouldn’t come as a surprise that, when social media are added to the marketing mix,
expenditures can decline.


The clustering engine of ORKASH technology demonstrated in this snapshot enables an overview of the themes under which the Brand is featuring in the media. Such an analysis enables assessment of the effectiveness of marketing campaign and for lead generation, as well as for competitive intelligence.

Addressing Consumer Dissatisfaction

An old adage : “It’s much more profitable to keep an existing customer than go looking for a new one.” This remains wise advice across the corporate world, but is often widely ignored in practice. Companies too often fail to respond to complaints in a timely manner, and risk losing the same customers they spent large sums acquiring in the first place.

Customer service professional nowadays do comprehend that poor experience no longer results in a customer telling 5 friends through word of mouth: but that they can instantly reach hundreds and thousands of people, courtesy reach of social media. Customers are taking their frustrations with products and services to sites like Twitter, Facebook and YouTube, in the knowledge that social media networks can generate more attention and faster responses than calling a customer service centre.

A response by the company on the social media itself, apart from assuaging the irate customer, also serves to project a positive image of the company to a host of social media spectators.


The pace of change, insofar as data and information is concerned, is accelerating beyond imagination. As a case in point, Facebook was founded in 2004 and Twitter in 2006. Yet, in less than a decade of their existence, such platforms are transforming the information exchange and social networking rules.

Companies, political parties and organisations across the globe are increasing their efforts to understand social media trends. For the era of gut instinct, to estimate personal preferences, may be all but over. Deciphering social media trends, backed by analytical tools, is the new dawn.

ORKASH technology has engineered analytical tools for all the above domains. The accompanying snapshots are representative of the social media analysis tools that ORKASH technology offers.

This screenshot of ORKASH technology identifies the users that are tweeting about Honda. The font size of the users twitter handle indicates its significance. A deeper analysis of influencers can be done from the sub features of Multi Handle analysis and Top Users Pie Chart.


, , , , , ,



– by ORKASH Labs, Copyright: ORKASH Services Pvt Ltd

Summary: In an unprecedented phenomenon the AAP has created a powerful impact in a very short term by its mere entry into national level politics.  ORKASH’s research here  uses social-media data (i.e. many millions of social media conversations) and game theory models to identify and analyse the forces that are shaping many new, but ‘fragile’,  trends  in the Indian political environment in the build up to the 2014 elections.  We find two major dimensions of AAP’s impact at the national level, namely:

  1. ‘rules of the game’ of the Indian politics have changed significantly, triggered by the AAP phenomena. However, how different parties would respond to these, internally at the organization level and externally in their strategies, is the new uncertainty.
  2. the statistics of the outcome of the 2014 elections, such as winning margins, vote-bank splits, voter polarization, vote swings, rural versus urban voting pattern divide, are all set to change. Political parties would do well to put the effort to interpret these and take the steps to accommodate and plan for the execution and operational implementation related changes these represent for their campaigning. (Even if the Aam Admi Party were to get a mere 5% of votes, it has the potential to emerge as a major influence factor in the election results, given the thin margins of victory that  are likely due to a three-way or four-way  split contest in a large majority of constituencies.)

Statistics show that the AAP seems to be developing into a national level phenomenon. The party has taken both the Social Media and the News Media by storm by becoming the most talked about Indian political party. Using Orkash’s Social Media Analytics platform to analyse data from Twitter, we can see some very interesting trends.

  • The AAP has over 16 lakh (1.6 million) tweets about it whereas the BJP and Congress lag behind at 14 lakh (1.4 million) and 11 lakh (1.1 million) respectively.
Graph 1

Jan 15 – Feb 15, 2014

Graph 1

  • The AAP is not just a North India or Delhi specific phenomenon as 41% of politics related tweets in South India discuss the party whereas the number is 34% in the North. Between 40-50% of tweets in South Indian cities like Bangalore, Chennai and Trivandrum discuss the AAP. Below we can see tweets on the AAP originating from cities, all over the country.
Graph 2

Jan 15 – Feb 15, 2014

These trends show the AAP appealing to a wider base than any small Regional party has managed in a long time.                   (Note: The numbers in smaller cities are relatively less, but statistically significant given their lower population)

Disrupting the National Level Political Equilibrium

The AAP, merely with its entry, is impacting the National level political dynamics.  To understand this we use a Game Theory model to depict the game of Indian Politics. Consider a line which depicts the electorate, and voters spread out uniformly in a linear fashion, along it. Each voter has only one vote.

 Line 1

We have two ‘National’ parties – the Congress and the BJP. They are the players of this game – C and B, respectively. The objective of the game is for the players to position themselves along the line in such a way, so as to garner the maximum share of the votes. The assumption is that voters vote for the candidate closest to them, in terms of position. In political terms, this would mean that voters vote for candidates who are most aligned with their voting priorities and that political parties take stands with the motive of garnering the maximum possible vote share. So in this two player game what have C and B been doing historically?

Line 2

The logic of the game suggests that the only place the two Players would strategically stabilize would be exactly at the center, such that both appeal to the median voter. By definition an equilibrium is a state of rest where no player has an incentive to shift from his/her position. In a game with players competing for vote share, this implies that at an equilibrium, the players are positioned such that no deviation by any player can bring it more vote share, no further gain can be made by deviating. This situation is thus, an equilibrium as there are no incentives to deviate. Consider any other combination of positions and you will see that in every case, incentives to deviate will exist. No other combination of positions, can be an equilibrium. Line 3Not an equilibrium case. Reason it out yourself.  

Enter a third player.

Unlike the national level, we have seen at the state level that the political environment is not just limited to two parties. Various regional players come into the picture.  Here we add a third player – A. If all three parties position themselves at the center, they each only manage 1/3rd share of the votes. Is this an equilibrium? No, were any one of them to shift slightly to the right or left, they would gain. 

Line 4

Consider any combination of positions in a 3 player game and you will see that with three players, no equilibrium is possible. 

Line 5

Think over the logic for the case above. It is not an equilibrium either. There is no stability in such a case, and players constantly change their position in response to another player’s actions. Stability can only come about if one player quits the game, or if two players decide to merge and reduce the game back to that of 2 players. Examining state level politics in states like Uttar Pradesh or Tamil Nadu we see that such dynamics have been at play for a while and have led to low victory margins and coalitions. Either the players cut each other’s vote share leading to narrow margins, or they join together (as coalition partners) to reduce the number of players and lend more stability to the game. In the 2009 elections, the average margin of victory in a parliamentary constituency was a mere 9.7 percent, the thinnest margin since independence, reflecting stiffer competition. We can see in the graph below, the median margins of victory across states in the 2009 General Elections. Notice that in the states of Andhra Pradesh, Bihar, Karnataka, Kerala, Tamil Nadu, Uttar Pradesh and West Bengal, where we see that regional parties are relatively more active, the median margin of victory lies between 5% and 10% only.Graph 3a

Graph 3b

Post 2009 Lok Sabha elections

AAP – the National Level third player

The entry of AAP is creating the same effect as state level regional parties, but at the National level.  The Aam Aadmi Party claims to have taken a stand different from what Indian politics had been accustomed to – No VIP Culture, No corruption, Moving past Caste and Community based politics and financial transparency regarding Party funding. What does this mean for politics? The AAP has refused to ally with any party with a dubious past which means it is unlikely that the National level political game will reduce to a two player game, unless the AAP ceases to be a significant player. If the National Level Political Game becomes a three player game – we will see disequilibrium.

The Congress and BJP will not be able to stick to their old strategies of wooing the median voter.

We take these stands of the Congress and BJP for granted to such an extent, that functioning outside of them seemed impossible. They ended up forming the rules within which politics was played. But with the emergence of the AAP we are seeing a perception change. Thus, in order to compete in the game, the Congress and BJP, must shift their stances strategically.

New rules will have to be written if the AAP establishes itself as a credible national player.

The AAP – Changing the Rules of Indian Politics

The AAP’s success in Delhi need not be replicated at the National Level, however it is clear that they are attempting to play the game outside of previously defined rules. Let us look in deeper at some of these and the changes we are seeing in the strategies of other parties, as a response.

Fielding Candidates who can get votes, irrespective of their Criminal past

The AAPs insistence on clean candidates for the Delhi elections as well as now for the Lok Sabha elections, and their direct challenge to MPs with corrupt pasts is a strategy which is causing much stress to other players. We are already seeing that the Congress and BJP, as a response, are unwilling to take the gamble of keeping their old corrupt candidates in the game. The Congress is thinking twice before providing a ticket to Suresh Kalmadi’s daughter or to Ashok Chavan, which would’ve been a no brainer for them in the past.

For the upcoming elections, the AAP effect will ensure that a Cleaner slate of candidates enters the arena.

Defying the Cast & Community based voting patterns

The AAP is making a concerted effort to ensure a wide appeal instead of being drawn into Caste and Community based politics. The party members proclaim themselves to be representatives of the ‘Aam Aadmi’. In the Delhi Assembly elections the AAP won 9 out of the 12 reserved category seats without appealing to these communities in particular. On the other hand Modi, for the first time, is being positioned as an OBC success story too woo the community. The downplaying of the BJP’s Hindutva stance and focus on governance in Modi’s national level election campaign has also been noticeable, displaying the strategy and focus areas of the BJP very clearly. Admittedly caste and community based politics makes up such a large part of the way Indian Politics is played out that major changes will take a while to manifest themselves.

The AAPs success or failure in positioning itself as a truly national party and it’s ability to sustain itself will be a huge factor in determining the future of caste and community based politics in India in the long run.

Clean Governance as an Agenda

As part of their agenda for Clean Governance, the AAP has been fighting for the Jan Lokpal bill resorting to high profile attention grabbing tactics on the issue.. They even dissolved their government when the bill was not passed in the Delhi Assembly, as per their demands.  The BJP has also been preaching an anti-corruption and good governance stand for this election which means that the AAP is directly competing with it in this domain. In the graphs below we see that the AAP is widely discussed in relation to clean governance and anti corruption on Twitter. The words anti and corruption are the most widely used negative words in relation to AAP, which when combined, tell us that it’s anti-corruption image has been well established. In terms of positive terms used with respect to the AAP we see – clean, good, support, right and free making up the largest shares. 

Graph 4a

Jan 15 – Feb 15, 2014


Graph 4b

Jan 15 – Feb 15, 2014

The VIP Culture

The AAP has refused  ‘Laal Battis’, high security and VIP accommodations. As a result, we have debates on the media and steps taken by several politicians to save their image. 

Ignoring the Aam Aadmi

The AAP claims to give people a voice versus decisions being taken purely by those elected. This has struck a chord with people as a result of which other parties are following suit. Janta Darbars are being organised in several states by different parties.

The Anti-VIP culture and Voice of the Common Man stands are more to build the party image and it is likely that most such efforts will be seen prior to elections. If the AAP includes the common man in it’s decision making process post elections and performs well, it is only then that such stands will grow beyond marketing gimmicks.

Party Funding

75% of the funding of the Congress and the BJP comes from unknown sources, allowing for corruption. Taking a different stand, the AAP publishes the details of all its donors, irrespective of the amount of donation. It also mentions the passport numbers of NRIs who donate to the AAP. People, the voters, have now seen that it is possible to play by different rules. This change in perception is the driving force behind the change in politics. An interesting interplay of strategies will be seen in the run up to these elections, in this situation of disequilibrium and uncertainty.

Likely Rifts and Shifts within Major Parties

Congress – The Congress party is at its lowest and will need to take drastic measures to redeem itself by disengaging with the rules of politics it is responsible for establishing.

In a step away from its usual High Command dominated selection of candidates, the Congress party is holding primaries (intra-party elections) to select candidates for some Lok Sabha seats.

Rahul Gandhi is being given greater responsibilities and a larger role to play. Cleaner candidates are being considered and the Congress party’s performance positives are being widely publicized. With the advent of newer cleaner candidates many of the well entrenched senior Congress members may not get the same leeway they earlier did, and many of them may even be denied a ticket. This will lead to confrontation within the party between the old and new. Rifts have already begun to be seen with many senior leaders unhappy with the primaries. The party structure is likely to shift in favour of the newer younger cleaner generation. These changes will take some time to manifest themselves but it is possible that these changes are just what the party needs to revamp it’s image.

BJP – A similar intra party change in structure will take place in the BJP, but the urgency may not be as high as that for Congress as the BJP has managed to create a strong campaign around Modi, helped by the anti-Congress mood in the country. The Modi campaign has been actively wooing the youth. A lot of young professionals have also been hired to run the campaign, and have come up with ideas like ‘Chai Pe Charcha’ and compilation of the book ‘Moditva’.  Over the past two weeks we see that the handles used on twitter, with respect to the BJP, are increasingly campaign oriented. Notice, there is hardly any mention of the BJP as a party. Modi leads the way with his new Chai Pe Charcha campaign, #namo4pm, #namoinkolkata, #namo and #yuva4namo entering the fray. 

Graph 5

Feb 1 – Feb 15, 2014

The success of the campaign, recently, can be better measured if we compare the shares of the political parties in twitter conversations over the past 5 weeks, to that over the past two weeks. We looked at the former in the beginning with the AAP at 39%, the BJP at 33% and the Congress at 27%. Below, we have the same graph but for the time period of 1/02/14 to 15/02/14.

We see that the BJP’s share in conversations has increased significantly in comparison to the overall, with the BJP now at 43%, the AAP at 40% and the Congress lagging far behind at a mere 16%.

Graph 6

Feb 1 – Feb 15, 2014

AAP – The AAP may have brought about interesting changes by its mere entry, however, after coming to power it has been involved in a lot of controversies. As a result there has been some degree of disenchantment with the party.The AAP needs to tread carefully and make sure it does not lose out on the support base it created. We analysed the twitter conversations regarding AAP with reference to controversies that have cropped up over the past few months. We see that the handles that show up in such a scenario, do give some insight into a degree of disenchantment with the party. Handles that crop up are #aapdrama, #quitaap, #dharna, #aapinaction, #bhagodakejri, #gamblecrumbles and #anarchy. On the other hand support bases also exist, in the form of handles like #arvindatcii, #karntikaariaapgovt, #rilgasscam and #yokejriwalsobrave.

Graph 7

Jan 15 – Feb 15, 2014

The AAP will need to perform well and think its actions through wherever it is elected. It is possible that they may be more successful in their drive against corruption and changing the system just by practicing activisim politics, without actually forming the government. Being in power forces them to look at numerous issues they haven’t thought out. It also makes them more vulnerable to attack by other parties as they are direct competition. Spreading thin their resources in order to win seats all over the country can lead to a dilution in ideology as the more people join a movement, the more views join in as well. Starting a nation wide campaign in a few short months is tough task and may lead to errors of judgement, which the Media will definitely latch onto. This will be a decision to take for the AAP as it moves forward, how can it be more successful – through activist politics or by getting into mainstream politics and attempting to govern, leaving itself more vulnerable to risks. This will determine whether the AAP will be able to sustain itself as a credible national force which in turn will determine the way Indian Politics will go in the future.

, , , , , ,


– by ORKASH Labs, Copyright: ORKASH Services Pvt Ltd

Given the unprecedented growth and reach of social media, monitoring what a company is doing on social media channels and what the people are talking about its products and services, has a huge potential for competetive intelligence gathering.  The forecast for such monitoring and the consequent business potential, is without doubt exciting for any corporate. The case for increased usage of social media analytics is getting more compelling, with every passing day.

To this end, Orkash has put together this blog post, which is an amalgamation of figures and case studies.  If you are interested in competetive intelligence, simply read on.

Some Trends

A study was conducted by the Center of Marketing Research at the University of Massachussets, to identify how Fortune 500 companies are using Social Media, as part of their marketing and customer service strategies.  77 percent have active Twitter accounts and 70 percent have an active Facebook presence (both up by 4% compared to the previous year, 2012). These companies are not just promoting their products & services and creating a digital marketing campaign, but have identified Social Media for customer engagement, for example, as an effective means of interacting with disgruntled customers as well.

Further, HubSpot’s 2013 survey shows that Social Media produces almost double the marketing leads of trade shows, telemarketing, direct mail or PPC ( Pay Per Click, an internet advertising model).

Case Study 1 : Predicting Sales – Automobile Sector

Social Media analysis of the Indian automobile sector was undertaken. The activities of a well known international car manufacturer (Brand X) were monitored on various social media websites by usings ORKASH’s social media mining and analytics tool.  Over the course of a few days, various types of information were extracted from Facebook and Twitter pages. This included data extration on various metrics such as trends and demographics associated with the ‘Likes’ on Facebook pages of various brands, ‘mentions’ count of the car brand in social media conversations, influence networks of the top users, sentiment and comparative analysis of comments, location specific trends, etc. This was also done simultaneously for a rival car brand (Brand Y) to better understand the user sentiments related to various parameters, and the sales pattern.


Fig : Sales figures obtained from Open source


Fig : Mentions on Facebook. This is an Orkash Technology output

A direct correlation between the sales figures and number of mentions was found on a month-on-month basis. However, at the time of the study (July 2013), sales figures till the month of May 2013 only were available, with the subsequent month figures awaited. The pattern of the sales could however be predicted since the social media activity, in terms of mention counts, for these months were already available. Once the sales data was released by the car manufacturer, it was found that the sales of Brand X increased in the same pattern as predicted by the Orkash tool – there existed a direct co-relation between the quantum of social media activity and sales. Such information is of tremendous value to business.

The snapshot below, obtained from the Orkash Clustering Engine technology, shows the grouping of important keywords and phrases associated with the brand, as they appear on social media platforms. For example, the specific problems, complaints and opinions on these issues, forms clusters based on the number of occurrences, showing the inter-connections. This kind of visual representation gives a comprehensive overview of the most common topics being discussed about a brand and the inter-relationship of these topics.


Fig : A cluster identifying Brand X problem areas. Orkash Technology Output

The Orkash tool was also able to classify which of the negative comments were complaints, and further subdivide them into various categories like quality, post-sales service, customer service etc. The locations of the origin of these complaints, in terms of which dealership or workshop in which city had a recurring problem, could also be identified by the system. The information was retrieved through the contextual analysis of text and content of the comments.

Orkash technology

Fig : Orkash Technology Output

Case Study 2 : Competetive Public Engagement – London Olympics  

In the build up to the 2012 London Olympics, Adidas struck a reported £40 million three-tier sponsorship deal to be the official sponsors for the games and launched their #takethestage campaign. In a classic case of competitive garnering of mileage on social media, Nike quickly countered the Adidas campaign by creating an all new #findgreatness campaign.   Figures from Socialbaker’s CheerMeter revealed that between July 27 to August 2 there were over 16,000 tweets associating the keyword Olympic with Nike, while Adidas received 9,295 tweets in the same period. Adidas gained over 80,000 new Facebook fans during the Olympics compared to more than 166,000 for Nike. The biggest sporting event in the world was a great platform to showcase the brand and increase awareness, but, as the numbers suggest, the battle on Social media was won by Nike, even though it was Adidas that spent big bucks sponsoring the London Olympics.

Case Study 3: Response to Digital Marketing : Food and Beverages Sector

The Orkash Clustering Engine technology has emerged as a very powerful tool in identifying brand activities like promotional campaigns and events, upcoming products and accumulating user sentiments and producing clusters showing their interconnections. A representation of this sort enables the brand to quickly identify problem areas, apart from ascertaining the outcome of their marketing strategies. The screenshot below, of a popular Indian liquor brand, shows the clusters obtained from social media conversations, just after the launch of a digital campaign. Key phrases like ‘Global Beer’, ‘Just want to Drink’, ‘New Brews’, ‘High Prices’ have the largest clusters and the maximum connections. This information culled out from Social media, which happens to be the platform consumers first turn to, can be of huge value to companies producing consumer goods.

Digital Marketing

The Future of Social Media Analytics in India

With its huge ‘youth demogrpahics’ driving India towards becoming one of the biggest Social Media market in next couple of years, it is becoming increasingly essential for companies to not rely solely on traditional media for the purpose of deriving business  insights. The approach of mining information from Social Media pages and conversations and using analytics to create deep insights into the activities of the brand, the user perceptions and trends related to various parameters is increasingly becoming highly relevant.

Unlike many ‘first world’ markets, India has a huge social and cultural diversity that has a very significant impact on consumer behaviour and consumptions patterns. This makes social media analytics and intelligence collection even more relavant, but with the caveat that such analytics must take social, demographic and cultural context into consideration for meaningful trends and insights to be arrived at.

In conclusion, unlike global organizations, Orkash, being a 100% Indian company, understands the local issues and dynamics, which is supported by in-house existence of social, behavioural, political, analytical and technical subject matter experts. This enables us to develop the technology keeping the local context in mind.  Thus, social media analytics, customised to the Indian market, is what Orkash can deliver.

, , , , , , ,

– by ORKASH Labs, Copyright: ORKASH Services Pvt Ltd

Social media has become a catalyst for civil mass movements and social unrest across the world. This includes upheaval in Tunisia and Egypt, Iranian election protests, disturbances to law and order across India in response to Delhi gang rape case in December 2012, Anna Hazare anti-corruption movement in India, the 2011 riots in London, etc. The list goes on.

This proliferation of Social media, especially through the ubiquitous mobile phone, coupled with bursting population in urban areas, poses an unprecedented challenge as well as an opportunity for Law Enforcement agencies across the world. Social media provides a powerful communication platform for organising protest and civil unrest; but on the other hand it can give government and police agencies with the means for real time intelligence, and, more importantly, the ability to intimately understand the ‘pulse and mood’ of the people; for example their reason for discontent and the underlying societal stress points of a community group. Social media also has a tremendous potential for creating accountability and governance transparency through ‘virtual’ non-intrusive partnerships between the police and the local communities.

Public Partnership for Policing – Boston Bombing

Take the case of the recent Boston Marathon terror bombing. Unlike the last time the continental United States was attacked, (11 Sep 2001, when social media sites like Facebook and Twitter were not even conceptualized), this time in Boston the social media platforms became a shared public repository for video and photos from the scene, with the people at large, as a result, becoming an active participant in the search for the terror perpetrators.

Consequently, the two plotters became the “target” for the social media communities, and not just a headline in the media. The FBI then decided to release photos of the alternative key suspects that they had identified. It is highly probable that FBI would have held on to the photos a bit longer and not actively engaged the public in the search, if the online narrative on social media was not running so fast and furious. Preemptive release of their photos by the FBI, and due pressure by the demand for instant information in the social media world, forced the terror suspects to move earlier than they had intended, forcing them into a series of mistakes.

In addition, during the three-day lockdown of Boston, over 80,000 people turned to smart phone apps, the Internet, and any available radio listening device to follow along with the Boston Police scanner. Consequently, the most trending hash tag on Twitter was #BostonPoliceScanner. All this resulted in an unparalleled public-police collaboration, as the Police advised most Bostonians to stay indoors, the social media became the medium for the resident communities to coordinate the city-wide lockdown as police went about ‘hunting’ the terror suspects. Residential communities followed instructions of the police and also spread the word on social media. Thus what emerged was a Public Partnership for Policing, underpinned on voluntary and community ownership.

Predictive Intelligence – London Riots

For the Law enforcement agencies, social media analytics can quickly pick up intelligence on high-risk behavior. This was demonstrated during London riots of 2011. After an initial lag, the London Metropolitan Police reportedly used social media data to predict occurrence of riots in specific localities. The algorithm was based on following logic flow. Geographic clusters of mobile phones were identified on a real time basis, using location data provided by Telecom operators. The mobile concentration were indicative of a mob or a crowd assembling at specific location. The cluster was then analyzed to rule out occurrences like a traffic jam or a large party/social gathering which could also result in concentration of mobiles in an area. Thereafter, the inter communication pattern between the mobiles in the concentrated area was studied. For example, within a traffic jam the inter- communication would be very low but high in case of a mob with malicious intent where the mob-leaders were found using twitter to organize the mob.

Once such a trend was identified, the ‘sentiment analysis’ of tweets within this mobile phone cluster helped ascertain use of ‘emotionally enraged or incensed’ language, and determine the ring leaders through identification of key nodes in the communication patterns of the identified mobile phone cluster. Thus, such pattern analysis gave an early warning of potential mob violence and the real-time state of the crowd’s/mob’s state of group psychology. Counter actions in such a scenario can include jamming of mobile phones of key influencers and pre-emptive arrests of the mob leaders, and more informed redeployment of Police resources for pre-emptive incident response.

Nirbhaya Rape Protests, Delhi

The unprecedented protests and social upheaval following the Nirbhaya gang rape in New Delhi, on 16 December 2012, was triggered in a large measure due to social media. As a representative example, Sikha (name changed), 19 years, was at Jantar Mantar monument on December 25 protesting against Nirbhaya’s brutal rape when Delhi Police swooped down, rounded her up along with other agitators and took them to the Parliament Street police station. Sikha fired tweet after tweet even as she was bundled into a police van. She went on broadcasting to the world all that was happening around her. “Illegally being held here at Parliament St Police Station Delhi w/ 15 other women. Terrified, pls RT,” she tweeted. It worked. In a flash, more than 1,700 people retweeted her SOS tweet. Social media analytics indicate that the message reached over two hundred thousand people and resulted in a sympathy wave leading to even greater protestors’ crowds.

As the protests escalated across the country, water cannons, baton charges, and tear gas were quick to be deployed on the streets, especially in New Delhi. In hindsight, pre-emptive intelligence picked up from social media could have helped mitigate or prevent such a volatile outcome. Most importantly, the sentiments and opinionsbeing expressed on social media could have provided the police with insights intoemotional and psychological stress points driving the protestors – the most importantfactor that the police agencies need to know to prevent escalation of the violence and to de-escalate such a situation.

Orkash Technology

The above screenshot of ORKASH Socia Media Intelligence Platform identifies  the geographic clusters of tweets when Nirbhaya rape case protests were in progress in Delhi in December 12. Further, this technology enables detailed automated analysis of the sentiments and behavioral aspects of the tweet contents, which indicated build up of resentment and fury in the protesting crowds, giving timely indication of the transformation of some segments of the crowd into a mob, and their psychological state.

This kind of analytics and data mining of social media feeds, however, requires a complex architiecture of unstructured-data mining tools, hardware and services, (and policy controls) in the form of a Social Media Intelligence platform because of the large amounts of data to be analysed in real time. This also needs a Data Sciences approach to sentiment and behavioral analysis of the comments and traffic patterns, and temporal analysis about anticipated events. None of these are easy or readily available technologies in the current state of things!

Community Engagement for Law and Order

A recent research report has established that nearly 45% of the 100 million plus Indian web users, most of them from urban areas, connect on social media to discuss politics and social issues. Only Arab countries scored higher than India on this account. Thus, any and every Indian state agency that is a stakeholder in the Law and Order domain will need to build up expertise on analyzing social media inputs, for this is an excellent platform for listening to community and public voices. As in other countries, it is a fact that urban India resides in high density pockets. These are invariably social or ethnic clusters in large cities, underpinned further by religious/regional/linguistic/community identities.

The young population in lower-income pockets of large cities are often defined by squalor and depravity of ‘urban ghettos’, and are forced to reconcile their dreams with their economic and social reality, which often makes them susceptible to crime, drugs, radicalization and even terrorism. The RWA’s (Resident Welfare Associations) or local community leaders in such pockets are an ideal channel for the Police to tap into, and grasp, the human angle context to crime and its prevention dynamics. However, such community policing is through traditional physical interface due to perceptions of intrusion or trust. In such situations, social media accords an ideal forum for the Police to engage with the ‘Mohalla’ or local community populace without an ‘intrusive’ forward presence. This has been done fairly successfully by the Police in UK in its policing programs for vulnerable community groups.

Various police forces across the world have set up a social media monitoring facilities. These “Social Media Labs” monitor the likes of Facebook, Twitter, Google+ and other prominent social media platforms to measure changes in mass moods and track matters concerning public law and order. Police teams across the globe are also keeping a vigil on widely discussed and trending topics, in order to tie social media and criminality together. The NYPD (New York Police Department) has a program to mine social media for information about “troublesome house parties, gang showdowns and other potential mayhem”, and so has Mumbai Police recently created a Social Media lab.

Future Challenges & Opportunities

The perennial challenge for any Police department is that the amount of data covered by social media posts, updates, and tweets, will be next to impossible to monitor using traditional technology. This requires large scale infrastructure and Big Data scale of mining and analytics for textual unstructured data alongwith automated cognitive and temporal analysis. ORKASH (www.orkash.com), alongwith the likes of IBM (the Watson project), is amongst a handful of companies worldwide with the technology to do so. Of course, the inevitable dilemma surrounds the issue of privacy. Without a warrant, what information should law enforcement be able to access? Where is the line to be drawn insofar as digital intrusion is concerned? In potentially life-threatening situations, should social networking sites provide information and personal details? Though such questions may remain unanswered in the near future, the peril would be greater if they remain unasked.

Police forces have regularly received a “shot fired” message via Twitter and suspicious person reports on Facebook. Additionally, in large scale disasters scenarios, e.g. earthquakes or large terror strike, Social Media can be used for seeking and arriving at ‘situational awareness’ and optimising the incident response efforts of emergency services in the rapidly changing and confusing scenario of a disaster. More about this in our next blog post.

In conclusion, in a manner similar to beat-patrols, the Police forces will need to patrol the virtual world of social media. Be it for ‘connecting’ with the people, community-police partnerships, demonstrating presence, picking up incidental information or analyzing the conversations for pre-emptive intelligence, social media accords an unprecedented opportunity.

The accompanying snapshots illustrate the Social Media Intelligence solution developed by ORKASH Labs. They can be customized for specific Policing requirements.

Assam Roits Final

This snapshot depicts network linkages generated form ORKASH’s Social Media Intelligence platform. The graph above reveals linkages between various twitter handles commenting on the Assam riots and the User IDs (blurred out) involved in spreading rumors and   provocative  content targeted at  one particular community in cities like Bangalore and Pune, which then led to exodus of people of North-eastern origin from these cities. Font size of the handle indicates its significance in terms of influence. 


, , , , , , , , , ,