Page 25 - ICDL 2019 - Background Paper
P. 25
the consequent challenge is to be able to analyse the large volumes of user generated content and the implicit (or
explicit) links between users, in order to glean meaningful insights therein.
The workshop will address interesting questions related to blogs, Twitter, and other social media platforms, including:
 Given the massive amount of user-generated content on the Web, how can we identify the subset of content
(blogs, forums, and so on) that discuss not only a specific entity, but higher-level concepts as well that are in
some way relevant to the product/brand/entity of interest?
 Having identified this subset of relevant content, how do we identify the most authoritative or influential
authors in this space?
 How do we detect and characterize the specific sentiment expressed about an entity (for example, product)
mentioned in a blog or forum?
 How do we tease apart the emerging topics of discussion from the constant chatter in the blogosphere and
other social media?
 How do we overcome the information overload and provide a rich and coherent user experience?
 How to deal with unreliable and often conflicting information? What notions of trust are appropriate?
The goal of this workshop is to formalize and address meaningful metrics and predictive tasks, as well as actionable
explanatory analysis, corresponding to the aforementioned objectives. This workshop will bring together researchers
in all related disciplines—from the academia, industry, and the government—and create a forum for discussing
recent advances in social media analysis. In doing so, we aim to better understand the practical requirements of this
domain and the limitations of our current methods, and to inspire research on new algorithms and techniques for
social media analytics.
19
explicit) links between users, in order to glean meaningful insights therein.
The workshop will address interesting questions related to blogs, Twitter, and other social media platforms, including:
 Given the massive amount of user-generated content on the Web, how can we identify the subset of content
(blogs, forums, and so on) that discuss not only a specific entity, but higher-level concepts as well that are in
some way relevant to the product/brand/entity of interest?
 Having identified this subset of relevant content, how do we identify the most authoritative or influential
authors in this space?
 How do we detect and characterize the specific sentiment expressed about an entity (for example, product)
mentioned in a blog or forum?
 How do we tease apart the emerging topics of discussion from the constant chatter in the blogosphere and
other social media?
 How do we overcome the information overload and provide a rich and coherent user experience?
 How to deal with unreliable and often conflicting information? What notions of trust are appropriate?
The goal of this workshop is to formalize and address meaningful metrics and predictive tasks, as well as actionable
explanatory analysis, corresponding to the aforementioned objectives. This workshop will bring together researchers
in all related disciplines—from the academia, industry, and the government—and create a forum for discussing
recent advances in social media analysis. In doing so, we aim to better understand the practical requirements of this
domain and the limitations of our current methods, and to inspire research on new algorithms and techniques for
social media analytics.
19
