Influence et contagion
6.0K views | +2 today
Follow
Influence et contagion
L'influence et la contagion dans la cyberculture
Curated by luiy
Your new post is loading...
Your new post is loading...
Scooped by luiy
Scoop.it!

Twitter #bots in class. You're here because of a robot | #datascience #agents #influence

Twitter #bots in class. You're here because of a robot | #datascience #agents #influence | Influence et contagion | Scoop.it
Note: This post is co-written with Piotr Sapieżyński Is it possible for a small computer science course to exert measurable influence (trending topics) on Twitter, a massive social network with hun...
luiy's insight:

A large part of our motivation for investigating Twitter bots in class is that the amount of manipulation that humans are experiencing on line is ever increasing. Think, for example, about how Facebook’s time-line filtering algorithm shapes the world view of hundreds of millions around the globe. And that’s just the most main stream example.

 

Social influence

 

As the course progressed, we focused on creating bots that could use machine learning to recognize “good” content for tweeting and retweeting. Bots that are able to detect topics within their tweet-stream … and distinguish between real, human accounts and robots among their followers.

However, the question remained: Can those thousands of followers  be converted to influence on Twitter? For the class’ final project, we decided to put that to the test.

The overall goal was to for each team to build a convincing bot, get human followers, and  at a specified time, for everyone work together to make specific hashtags trend on twitter. So how to achieve that goal? Here’s an overview of what each team has worked on:

 

- Build convincing avatars and use the high follower-counts as part of the disguise. 

 

- Use machine learning to tell who’s a bot and who’s not (in order to focus only on humans and ignoring bots). 

 

- Use natural language processing & machine learning to discover quality content to re-tweet and tweet. 

 

- Use network theory, to explore the network surrounding existing followers, making sure that bot actions reach entire communities.

more...
No comment yet.
Scooped by luiy
Scoop.it!

How Gangnam Style" Went #Viral | #SNA #contagion #datascience

How Gangnam Style" Went #Viral | #SNA #contagion #datascience | Influence et contagion | Scoop.it
Data scientists trace how the most-viewed video in YouTube history spread across the Internet
luiy's insight:

When South Korean pop star Psy released his “Gangnam Style” video in 2012 it spread like wildfire. Researchers at Indiana University Bloomington tracked the spreading meme by following how Twitter users shared the video with friends and strangers alike. By the time 200 tweets had linked to the video among the subset of Twitter users studied, “Gangnam Style” had already reached 86 different communities of users (blue nodes). After 3,000 tweets the meme had spread to nearly 1,000 different communities (green). “Gangnam Style” soon became the most-viewed video in YouTube history; by late 2013, the video had amassed more than 1.8 billion views.

more...
No comment yet.
Rescooped by luiy from Social Network Analysis Applications
Scoop.it!

The Network Secrets of Great #Change #Agents | #SNA #influence

The Network Secrets of Great #Change #Agents | #SNA #influence | Influence et contagion | Scoop.it
Business management magazine, blogs, case studies, articles, books, and webinars from Harvard Business Review, addressing today's topics and challenges in business management.

Via Premsankar Chakkingal
luiy's insight:

In tracking 68 of these initiatives for one year after their inception, we discovered some striking predictors of change agents’ success. The short story is that their personal networks—their relationships with colleagues—were critical. More specifically, we found that:

 

1. Change agents who were central in the organization’s informal network had a clear advantage, regardless of their position in the formal hierarchy.

 

2. People who bridged disconnected groups and individuals were more effective at implementing dramatic reforms, while those with cohesive networks were better at instituting minor changes.

 

3. Being close to “fence-sitters,” who were ambivalent about a change, was always beneficial. But close relationships with resisters were a double-edged sword: Such ties helped change agents push through minor initiatives but hindered major change attempts.

 

more...
Premsankar Chakkingal's curator insight, February 1, 2014 12:54 AM
Change is hard, especially at large organizations. But some leaders do succeed at transforming their workplaces. How? The secret lies in how they understand and mobilize their informal networks:
Scooped by luiy
Scoop.it!

#Virality Prediction and Community Structure in Social Networks | #SNA #memes #contagion

#Virality Prediction and Community Structure in Social Networks | #SNA #memes #contagion | Influence et contagion | Scoop.it
How does network structure affect diffusion? Recent studies suggest that the answer depends on the type of contagion. Complex contagions, unlike infectious diseases (simple contagions), are affected by social reinforcement and homophily.
luiy's insight:

Our method aims to discover viral memes. To label viral memes, we rank all memes in our dataset based on numbers of tweets or adopters, and define a percentile threshold. A threshold of θT or θUmeans that a meme is deemed viral if it is mentioned in more tweets than θT% of the memes, or adopted by more users than θU% of the memes, respectively. All the features are computed based on the first 50 tweets for each hashtag h. Two baselines are set up for comparison. Random guessselects nviral memes at random, where nviral is the number of viral memes in the actual data.Community-blind prediction employs the same learning algorithm as ours but without the community-based features. We compute both precision and recall for evaluation; the former measures the proportion of predicted viral memes that are actually viral in the real data, and the latter quantifies how many of the viral memes are correctly predicted. Our community-based prediction excels in both precision and recall, indicating that communities are helpful in capturing viral memes (Fig. 5). For example, when detecting the most viral memes by users (θU = 90), our method is about seven times as precise as random guess and over three times as precise as prediction without community features. We achieve a recall over 350% better than random guess and over 200% better than community-blind prediction. Similar results are obtained using different community detection methods or different types of social network links (see SI).

more...
No comment yet.