Goto

Collaborating Authors

Wu

AAAI Conferences

The share of videos in the internet traffic has been growing, therefore understanding how videos capture attention on a global scale is also of growing importance. Most current research focus on modeling the number of views, but we argue that video engagement, or time spent watching is a more appropriate measure for resource allocation problems in attention, networking, and promotion activities. In this paper, we present a first large-scale measurement of video-level aggregate engagement from publicly available data streams, on a collection of 5.3 million YouTube videos published over two months in 2016. We study a set of metrics including time and the average percentage of a video watched. We define a new metric, relative engagement, that is calibrated against video properties and strongly correlate with recognized notions of quality. Moreover, we find that engagement measures of a video are stable over time, thus separating the concerns for modeling engagement and those for popularity -- the latter is known to be unstable over time and driven by external promotions. We also find engagement metrics predictable from a cold-start setup, having most of its variance explained by video context, topics and channel information -- R2 0.77. Our observations imply several prospective uses of engagement metrics -- choosing engaging topics for video production, or promoting engaging videos in recommender systems.


Beyond Views: Measuring and Predicting Engagement in Online Videos

AAAI Conferences

The share of videos in the internet traffic has been growing, therefore understanding how videos capture attention on a global scale is also of growing importance. Most current research focus on modeling the number of views, but we argue that video engagement, or time spent watching is a more appropriate measure for resource allocation problems in attention, networking, and promotion activities. In this paper, we present a first large-scale measurement of video-level aggregate engagement from publicly available data streams, on a collection of 5.3 million YouTube videos published over two months in 2016. We study a set of metrics including time and the average percentage of a video watched. We define a new metric, relative engagement, that is calibrated against video properties and strongly correlate with recognized notions of quality. Moreover, we find that engagement measures of a video are stable over time, thus separating the concerns for modeling engagement and those for popularity -- the latter is known to be unstable over time and driven by external promotions. We also find engagement metrics predictable from a cold-start setup, having most of its variance explained by video context, topics and channel information -- R2=0.77. Our observations imply several prospective uses of engagement metrics -- choosing engaging topics for video production, or promoting engaging videos in recommender systems.


Vonage adds video engagement to contact center applications

ZDNet

Vonage has updated its Vonage Contact Center suite with video engagement, omnichannel chat, external routing for messages and cases and virtual assistants. The effort for Vonage highlights how the company has evolved from its voice over IP days to become a communication as a service provider. Vonage added that its Vonage Contact Center (VCC) suite is embedded in Salesforce, Microsoft Dynamics and ServiceNow.


How to Increase Engagement on Facebook Videos

#artificialintelligence

Videos are a crucial component of your content marketing strategy. Once your videos are created, you need to distribute them on as many channels as possible. With more than 2.2 billion monthly active users, it's only logical for Facebook to be one of those distribution platforms. Overall, this should be a winning strategy for your business. According to research, 90% of consumers report that videos help them making purchasing decisions. And 64% of people say that watching a video increases their chances of buying something.


Iggy Azalea and Nick Young break up: I've tried to rebuild my trust in him, she says, but I can't

Los Angeles Times

"Unfortunately although I love Nick and have tried and tried to rebuild my trust in him - It's become apparent in the last few weeks I am unable to," the "Fancy" rapper, 26, said Sunday on Instagram. The breakup announcement was timed well to coincide with the start of the NBA's Game 7 between the Cleveland Cavaliers and the Golden State Warriors, when one might presume that most basketball fans would be otherwise occupied. Young was more succinct in his notice, which was posted around the same time as hers: "Single," he tweeted. The couple, who got engaged in June 2015 when he gave her a big rock during his 30th birthday party, had been on the relationship rocks since a video went viral in March in which he was talking to teammate D'Angelo Russell about meeting up with a 19-year-old woman last summer after clubbing. Awkward tidbit: The video was reportedly shot by Russell right around the time of the engagement.