Transformation of threats in the information space: from technological to social. Part III
Is it permissible for the biased interpretation of the opinions of 1448 Americans, with the active informational pressure from the US state media, to be the beginning of World War III? And does humanity have protection from the “interested” actions of a small group of politicians? Modern technologies Online Big Data & Analytics have violated the know-how of the “hawks” about the opinion of the entire population, as they allow us to get a realistic assessment of the statements and moods of people in countries and the whole world.
Yes, of course, the creation of the “Shield for Peace” leads to the next development of the “Sword of War” (use of bots, individual point effects on LOMs (opinion leaders), situational informational impact, etc.) - the confrontation between Shield and Sword never stops. But let's talk about this another time. Or we will not talk - the topic of National Information Security became in 2013 a priority for all developed countries of the world, and many earlier public developments receive the “national security” stamp.
It is still “possible” to reveal some technological features and social aspects of the “Shield”.
In July 2013, according to a Reuters / Ipsos survey, over 70% of the US population opposed an armed attack on Syria. The active information processing "Assad used chemical weapons against civilians" and the subsequent (August 19-23) poll of "people" (as many as 1,448 Americans) brought the situation to the brink of war: "Already only half (56%) of Americans oppose the attack on Syria" .
The result of the information artillery preparation - on August 31, the world froze in anticipation of Obama's speech: would the “Nobel Peace Laureate” declare war on Syria?
')
In order to find out how much the picture in the media corresponds to the real situation, we conducted an express study, after collecting and analyzing 1.7 million messages in 2 days, we do not publish the full version in order not to litter Habr with the policy, with brief results can be found at the end of the article.
And now let us open the veil of the SHIELD secret, which allows us to obtain a reliable analysis of situations and events in real time.
Peak thematic information flow determines the real-time capabilities of OBD & A systems for:
The case with Syria allowed “in combat mode” to test the capabilities of the iLook Platform and the OBD & A BrandAnalytics class systems , and determine the technological limitations of the system (MongoDB, Elasticsearch, Gearman, Memcached, MySQL, PHP, C #):
1. The key words in various languages ​​are collected about the subject - the whole system recognizes 17 languages, the use of search with a distance and other operators of the language of search queries allows you to customize the search as accurately as possible. For example, we can set the search in this way “Obama Syria” ~ 7 - this will allow you to find messages that mention Obama and Syria within 7 words between them. Thus, the messages “Obama’s decision to deliver a direct air strike on Syria” will add to the topic of analysis, and news digests like “1. Obama is walking in Paris: photo! 2. ... 3. ... 10. George Clooney starred in a film about Syria "- no.
2. Messages are analyzed by the emotional coloring (tonality) of messages - the linguistic objective tonality allows you to automatically determine the emotion of messages in relation to a given object. For example, the message “Ivan is a wonderful person, he told Peter that Fyodor is a scoundrel”: positively to the object “Ivan”, to the object “Peter” - neutral, and to “Fyodor” - negatively.
3. Messages are geolocated - a multiparametric analysis of the author’s public profile data, the texts of his public messages and the environment is used, the information is updated with each new author message. The received data is processed through its own geo-dictionaries. Thus, if the author’s profile indicates - Miami, and he is daily checked in at the coffee house in Butovo - we are geolocating him in Moscow.
4. Collected messages are automatically analyzed for the presence of reposts / retweets / fuzzy duplicates - we identify popular points of view, get rid of spammers and stuffing.
5. Analyzes information about the audience - the number of subscribers of each author at the time of publication of the message. The counting algorithm is individual for each social network and takes into account its features.
6. Automatically formed message ratings - by audience, duplicate, comments, and so on.
Analysts have a minimum of effort - to evaluate these systems, identify existing trends and predict the development of the situation.
What do we get at the output?
The graph shows the number of messages for August 31: the peak - the expectation and speech of Obama about the appeal to Congress for permission to attack Syria:
The purpose of the study is to answer the following questions:
1. How actively are people from different countries discussing the situation in Syria.
2. How do residents of the largest NATO countries and Turkey feel about a possible attack on Syria.
3. Who is considered guilty in this situation: Assad or the opposition.
Characteristics of the study:
1. Duration: 48 hours (2 days)
2. Period: from 6:00 pm August 30 - 6:00 pm September 1
3. Number of messages: 1,745,549
4. Number of unique authors: 605 484
5. Number of countries: 241 countries (11,397 settlements)
The research was conducted in the main social networks: Facebook, Twitter, Vkontakte, Livejournal, Youtube, etc. The references were studied on the topic of the conflict in Syria and the preparation of the military operation of the Western countries against this country.
The most active discussion on the situation in Syria has unfolded in the US Internet space (46% of posts). In second place is the United Kingdom (14%). In Russia (the Russian-speaking traffic is about 1% of the world), the topic of Syria is 4% of the world total.
The vast majority of users of social networks in all countries opposed the invasion of Western countries in Syria. The most pronounced rejection of intervention is in Russia (in 94% of communications), France (90%), Germany (88%), slightly lower in the UK (84%) and the USA (83%). In Turkey, criticism of the upcoming Western operation against Syria is contained in 64% of the messages.
In the US social media segment, users tend to blame the Assad government (64% of posts) for the current situation in Syria, rather than the rebels (36%), they also think in Germany (58% and 42%, respectively) and Turkey (70% vs. 30%). respectively). On the contrary, in the UK, the majority sees the guilt of the rebels (57%), and not of the regime (43%). In France, opinions were divided almost equally (51% vs. 49%, respectively), in Russia, the perpetrators are clearly considered to be the rebels (96% of the reports).
1. The most active situation with Syria was discussed in the US online space.
2. The overwhelming majority (over 85%) are against attack.
3. In the USA and Germany, the population is inclined to blame the Assad government for the current situation; in Russia and the UK, most consider the rebels guilty.
In October, conducted polls in various NATO countries, showed 70-82% of opponents of the invasion of Syria. Conclusions can do yourself.
In 2014, we are planning new “global” studies, for which we need to raise the bar of technological thresholds several times, and also invite new partners who have experience in the field of visualization (Online) of Big Data, building social graphs and coloring links, applied artificial intelligence, automatic building of templates for identifying meaningful content, semantic text analysis, applying ontological models, identifying new trends, adaptive emotional coloring, sociologists, “highloaders” - all who work in related fields.
The nearest big game for OBD & A and operational sociology will undoubtedly be the 2014 Olympics, we are planning to share the results here at Habré, as well as at the annual Grushinsky Readings (not to be confused with the music Grushinsky Festivals :)) - the largest annual Russian sociological conference where for the first time there will be a special section dedicated to the use of modern technologies for online monitoring and sociological research in social media.
It's great that Russian technological developments in the OBD & A segment are at the global level, and it will be interesting to “butt” with world leaders (a month ago Apple bought TopSy, a company specializing in collecting and analyzing Twitter messages, widely known for monitoring US presidential elections, for $ 200 million ) - so, friends, welcome! - interesting projects and new technological solutions are waiting for us :)
Yes, of course, the creation of the “Shield for Peace” leads to the next development of the “Sword of War” (use of bots, individual point effects on LOMs (opinion leaders), situational informational impact, etc.) - the confrontation between Shield and Sword never stops. But let's talk about this another time. Or we will not talk - the topic of National Information Security became in 2013 a priority for all developed countries of the world, and many earlier public developments receive the “national security” stamp.
It is still “possible” to reveal some technological features and social aspects of the “Shield”.
Combat start
In July 2013, according to a Reuters / Ipsos survey, over 70% of the US population opposed an armed attack on Syria. The active information processing "Assad used chemical weapons against civilians" and the subsequent (August 19-23) poll of "people" (as many as 1,448 Americans) brought the situation to the brink of war: "Already only half (56%) of Americans oppose the attack on Syria" .
The result of the information artillery preparation - on August 31, the world froze in anticipation of Obama's speech: would the “Nobel Peace Laureate” declare war on Syria?
')
In order to find out how much the picture in the media corresponds to the real situation, we conducted an express study, after collecting and analyzing 1.7 million messages in 2 days, we do not publish the full version in order not to litter Habr with the policy, with brief results can be found at the end of the article.
And now let us open the veil of the SHIELD secret, which allows us to obtain a reliable analysis of situations and events in real time.
Technological characteristics of OBD & A
- Technological data collection: 5.000 messages per second
- Information flow (without duplicates): 17-18 million messages per day (200 / s)
- Peak thematic information flow: 60 messages / sec
Peak thematic information flow determines the real-time capabilities of OBD & A systems for:
- Automatic determination of tonality;
- Geolocation messages;
- Calculation of (un) clear duplicates (retweets, reposts);
- Calculation of the audience of authors;
- A variety of top ratings (frequency words, authors, countries, settlements, etc.).
The case with Syria allowed “in combat mode” to test the capabilities of the iLook Platform and the OBD & A BrandAnalytics class systems , and determine the technological limitations of the system (MongoDB, Elasticsearch, Gearman, Memcached, MySQL, PHP, C #):
- Thematic information flow - 10 million messages per day;
- Automatic determination of tonality (the slowest module) - 100 kb / s in one stream.
How it works from a “human” point of view.
1. The key words in various languages ​​are collected about the subject - the whole system recognizes 17 languages, the use of search with a distance and other operators of the language of search queries allows you to customize the search as accurately as possible. For example, we can set the search in this way “Obama Syria” ~ 7 - this will allow you to find messages that mention Obama and Syria within 7 words between them. Thus, the messages “Obama’s decision to deliver a direct air strike on Syria” will add to the topic of analysis, and news digests like “1. Obama is walking in Paris: photo! 2. ... 3. ... 10. George Clooney starred in a film about Syria "- no.
2. Messages are analyzed by the emotional coloring (tonality) of messages - the linguistic objective tonality allows you to automatically determine the emotion of messages in relation to a given object. For example, the message “Ivan is a wonderful person, he told Peter that Fyodor is a scoundrel”: positively to the object “Ivan”, to the object “Peter” - neutral, and to “Fyodor” - negatively.
3. Messages are geolocated - a multiparametric analysis of the author’s public profile data, the texts of his public messages and the environment is used, the information is updated with each new author message. The received data is processed through its own geo-dictionaries. Thus, if the author’s profile indicates - Miami, and he is daily checked in at the coffee house in Butovo - we are geolocating him in Moscow.
4. Collected messages are automatically analyzed for the presence of reposts / retweets / fuzzy duplicates - we identify popular points of view, get rid of spammers and stuffing.
5. Analyzes information about the audience - the number of subscribers of each author at the time of publication of the message. The counting algorithm is individual for each social network and takes into account its features.
6. Automatically formed message ratings - by audience, duplicate, comments, and so on.
Analysts have a minimum of effort - to evaluate these systems, identify existing trends and predict the development of the situation.
What do we get at the output?
Case 4. Military operation of the West against Syria: global monitoring of public opinion in social media
The graph shows the number of messages for August 31: the peak - the expectation and speech of Obama about the appeal to Congress for permission to attack Syria:
The purpose of the study is to answer the following questions:
1. How actively are people from different countries discussing the situation in Syria.
2. How do residents of the largest NATO countries and Turkey feel about a possible attack on Syria.
3. Who is considered guilty in this situation: Assad or the opposition.
Characteristics of the study:
1. Duration: 48 hours (2 days)
2. Period: from 6:00 pm August 30 - 6:00 pm September 1
3. Number of messages: 1,745,549
4. Number of unique authors: 605 484
5. Number of countries: 241 countries (11,397 settlements)
The research was conducted in the main social networks: Facebook, Twitter, Vkontakte, Livejournal, Youtube, etc. The references were studied on the topic of the conflict in Syria and the preparation of the military operation of the Western countries against this country.
The most active discussion on the situation in Syria has unfolded in the US Internet space (46% of posts). In second place is the United Kingdom (14%). In Russia (the Russian-speaking traffic is about 1% of the world), the topic of Syria is 4% of the world total.
Western invasion of Syria: the attitude of users of social networks
The vast majority of users of social networks in all countries opposed the invasion of Western countries in Syria. The most pronounced rejection of intervention is in Russia (in 94% of communications), France (90%), Germany (88%), slightly lower in the UK (84%) and the USA (83%). In Turkey, criticism of the upcoming Western operation against Syria is contained in 64% of the messages.
Who is to blame for the situation: Assad or the opposition
In the US social media segment, users tend to blame the Assad government (64% of posts) for the current situation in Syria, rather than the rebels (36%), they also think in Germany (58% and 42%, respectively) and Turkey (70% vs. 30%). respectively). On the contrary, in the UK, the majority sees the guilt of the rebels (57%), and not of the regime (43%). In France, opinions were divided almost equally (51% vs. 49%, respectively), in Russia, the perpetrators are clearly considered to be the rebels (96% of the reports).
General brief analytics:
1. The most active situation with Syria was discussed in the US online space.
2. The overwhelming majority (over 85%) are against attack.
3. In the USA and Germany, the population is inclined to blame the Assad government for the current situation; in Russia and the UK, most consider the rebels guilty.
Results of sanity
In October, conducted polls in various NATO countries, showed 70-82% of opponents of the invasion of Syria. Conclusions can do yourself.
Plans and cooperation
In 2014, we are planning new “global” studies, for which we need to raise the bar of technological thresholds several times, and also invite new partners who have experience in the field of visualization (Online) of Big Data, building social graphs and coloring links, applied artificial intelligence, automatic building of templates for identifying meaningful content, semantic text analysis, applying ontological models, identifying new trends, adaptive emotional coloring, sociologists, “highloaders” - all who work in related fields.
The nearest big game for OBD & A and operational sociology will undoubtedly be the 2014 Olympics, we are planning to share the results here at Habré, as well as at the annual Grushinsky Readings (not to be confused with the music Grushinsky Festivals :)) - the largest annual Russian sociological conference where for the first time there will be a special section dedicated to the use of modern technologies for online monitoring and sociological research in social media.
It's great that Russian technological developments in the OBD & A segment are at the global level, and it will be interesting to “butt” with world leaders (a month ago Apple bought TopSy, a company specializing in collecting and analyzing Twitter messages, widely known for monitoring US presidential elections, for $ 200 million ) - so, friends, welcome! - interesting projects and new technological solutions are waiting for us :)
Source: https://habr.com/ru/post/210150/
All Articles