What Makes People Watch Online Videos

Lagger, Christoph; Lux, Mathias; Marques, Oge

doi:10.1145/3034706

Cited by 14 publications

(23 citation statements)

References 10 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Several studies used frameworks to describe video-watching motivations. In 2006, Lagger et al [7] conducted interviews and surveys to describe viewer motivations. This framework included intentions of entertainment, boredom, music, information, product reviews, news, and learning.…”

Section: Related Workmentioning

confidence: 99%

“…Motivations for information were found to be relatively strong for online watching compared to television. Furthermore, emotional motivations were consistently important across studies [3,7,8,13]. Using 16 basic human motivations (e.g., power, knowledge, companionship, etc.)…”

Section: Related Workmentioning

confidence: 99%

“…Previous research typically focused on describing specific content areas [9,13] and experiences [4,10,11,12,14,15,16,17] of viewer motivations. Important frameworks for understanding viewer motivations were developed [3,7,8,13]. However, these frameworks fall short in at least one of three aspects.…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

YouTube needs

Oliveira¹,

Pentoney²,

Pritchard-Berman³

2018

Proceedings of the 20th International Conference on Human-Computer Interaction With Mobile Devices and Services

View full text Add to dashboard Cite

Watching online videos on mobile devices has been massively present in people's daily activities. However, different users can watch the same video for different purposes, and hence develop different expectations for their experience. Understanding people's motivations for watching videos on mobile can help address this problem by giving designers the information needed to craft the whole watching journey better adapting to user's expectations. To obtain this understanding, a comprehensive framework of viewer motivations is necessary. We present research that provides several contributions to understanding mobile video watchers: a thorough framework of user motivations to watch videos on mobile devices, a detailed procedure for collecting and categorizing these motivations, a set of challenges that viewers experience to address each motivation, insights on usage of mobile and non-mobile devices, and design recommendations for video sharing systems.

show abstract

Section: Related Workmentioning

confidence: 99%

Section: Related Workmentioning

confidence: 99%

See 1 more Smart Citation

YouTube needs

Oliveira¹,

Pentoney²,

Pritchard-Berman³

2018

Proceedings of the 20th International Conference on Human-Computer Interaction With Mobile Devices and Services

View full text Add to dashboard Cite

show abstract

“…User intent in the area of multimedia can in general be divided in the domains of image and video search [23]. In each of the two domains, several models and categories of intent have been defined, which are conceptually similar, but named differently in different publications [15,27,25,18].…”

Section: Introductionmentioning

confidence: 99%

Multimodal analysis of user behavior and browsed content under different image search intents

Soleymani

Riegler

Halvorsen

2018

Int J Multimed Info Retr

View full text Add to dashboard Cite

The motivation or intent of a search for content may vary between users and use-cases. Knowledge and understanding of these underlying objectives may therefore be important in order to return appropriate search results, and studies of user search intent are emerging in information retrieval to understand why a user is searching for a particular type of content. In the context of image search, our work targets automatic recognition of users' intent in an early stage of a search session. We have designed seven different search scenarios under the intent conditions of finding items, re-finding items and entertainment. Moreover, we have collected facial expressions, physiological responses, eye gaze and implicit user interactions from 51 participants who performed seven different search tasks on a custom-built image retrieval platform, and we have analyzed the users' spontaneous and explicit reactions under different intent conditions. Finally, we trained different machine learning models to predict users' search intent from the visual content of the visited images, the user interactions and the spontaneous responses. Our experimental results show that after fusing the visual and user interaction features, our system achieved the F-1 score of 0.722 for classifying three classes in a user-independent cross-validation. Eye gaze and implicit user interactions, including mouse movements and keystrokes are the most informative features. In summary, the most promising results are obtained by

show abstract

“…User intent in the area of multimedia can in general be divided in the domains of image and video search [22]. In each of the two domains, several models and categories of intent have been de ned, which are conceptually similar, but named di erently in di erent publications [14,17,24,26].…”

Section: Introductionmentioning

confidence: 99%

Multimodal Analysis of Image Search Intent

Soleymani

Riegler

Halvorsen

2017

Proceedings of the 2017 ACM on International Conference on Multimedia Retrieval

View full text Add to dashboard Cite

Users search for multimedia content with di erent underlying motivations or intentions. Study of user search intentions is an emerging topic in information retrieval since understanding why a user is searching for a content is crucial for satisfying the user's need. In this paper, we aimed at automatically recognizing a user's intent for image search in the early stage of a search session. We designed seven di erent search scenarios under the intent conditions of nding items, rending items and entertainment. We collected facial expressions, physiological responses, eye gaze and implicit user interactions from 51 participants who performed seven di erent search tasks on a custom-built image retrieval platform. We analyzed the users' spontaneous and explicit reactions under di erent intent conditions. Finally, we trained machine learning models to predict users' search intentions from the visual content of the visited images, the user interactions and the spontaneous responses. A er fusing the visual and user interaction features, our system achieved the F-1 score of 0.722 for classifying three classes in a userindependent cross-validation. We found that eye gaze and implicit user interactions, including mouse movements and keystrokes are the most informative features. Given that the most promising results are obtained by modalities that can be captured unobtrusively and online, the results demonstrate the feasibility of deploying such methods for improving multimedia retrieval platforms. CCS CONCEPTS •Information systems → Image search; Search interfaces; •Humancentered computing → Laboratory experiments;

show abstract

What Makes People Watch Online Videos

Cited by 14 publications

References 10 publications

YouTube needs

YouTube needs

Multimodal analysis of user behavior and browsed content under different image search intents

Multimodal Analysis of Image Search Intent

Contact Info

Product

Resources

About