Collaborating Authors


AAAI Conferences

Online platforms are an increasingly popular tool for people to produce, promote or sell their work. However recent studies indicate that social disparities and biases present in the real world might transfer to online platforms and could be exacerbated by seemingly harmless design choices on the site (for example: recommendation systems or publicly visible success measures). In this paper we analyze an exclusive online community of teams of design professionals called Dribbble and investigate apparent differences in outcomes by gender. Overall, we find that men produce more work, and are able to show it to a larger audience thus receiving more likes. Some of this effect can be explained by the fact that women have different skills and design different images.


AAAI Conferences

The emergence of online platforms allowing to mix self publishing activities and social networking offers new possibilities for building online reputation and visibility. In this paper we present a method to analyze the online popularity that takes into consideration both the success of the published content and the social network topology. First, we adapt the Kohonen self organizing maps in order to cluster the users of online platforms depending on their audience and authority characteristics. Then, we perform a detailed analysis of the manner nodes are organized in the social network. Finally, we study the relationship between the network local structure around each node and the corresponding user's popularity. We apply this method to the MySpace music social network. We observe that the most popular artists are centers of star shaped social structures and that it exists a fraction of artists who are involved in community and social activity dynamics independently of their popularity. This method based on a learning algorithm and on network analysis appears to be a robust and intuitive technique for a rich description of the online behavior.

How to Create Powerful Social Network Platform in 8 Steps


How did Mark Zuckerberg change the world? He built a global community that brings people closer together. The origins of Facebook are available to the general public. Everyone is familiar with the story of building social network platform that will greatly impact human relations and economy. Mark's vision of community opened a door to many variations of social media network platforms that today exist. Jack Dorsey created Twitter in March 2006. Rome may not have been built in a day, but Twitter was built in just two weeks, says Jack.

TWIMLcon: AI Platforms - Machine and deep learning in the enterprise


TWIMLcon: AI Platforms is brought to you by the team behind the TWIML AI Podcast (a.k.a. The conference has its roots in a series of interviews on the topic of AI Platforms published back in the fall of 2018. The series--which featured interviews with ML Platforms and Infrastructure engineers and leaders from Facebook, Airbnb, LinkedIn, OpenAI, Shell and Comcast--resonated very strongly with listeners and remains one of our most popular series to this day. We're excited to convene TWIMLcon: AI Platforms and provide the broader community of folks that care about productionalizing, operationalizing and scaling ML & AI an opportunity to share, learn, and connect with one another.


AAAI Conferences

Social networks are often grounded in spatial locality where individuals form relationships with those they meet nearby. However, the location of individuals in online social networking platforms is often unknown. Prior approaches have tried to infer individuals' locations from the content they produce online or their online relations, but often are limited by the available location-related data. We propose a new method for social networks that accurately infers locations for nearly all of individuals by spatially propagating location assignments through the social network, using only a small number of initial locations. In five experiments, we demonstrate the effectiveness in multiple social networking platforms, using both precise and noisy data to start the inference, and present heuristics for improving performance. In one experiment, we demonstrate the ability to infer the locations of a group of users who generate over 74% of the daily Twitter message volume with an estimated median location error of 10km. Our results open the possibility of gathering large quantities of location-annotated data from social media platforms.