Smitashree Choudhury

• Analyst at IBM

Social media has become a prime place where many users announce their personal events, such as getting married, graduating, or having a baby, to name a few. It is common for users to post about such events and receive attention from their friends. Such events are often sought after by social platforms to enrich users timelines, to create life-log v...

In this paper we propose an unsupervised lexicon-based approach to detect the sentiment polarity of user comments in YouTube. Polarity detection in social media content is challenging not only because of the existing limitations in current sentiment dictionaries but also due to the informal linguistic styles used by users. Present dictionaries fail...

This paper describes an ongoing prototypical framework to annotate and retrieve web videos with light semantics. The proposed framework reuses many existing vocabularies along with a video model. The knowledge is captured from three different information spaces (media content, context, document). We also describe ways to extract the semantic conten...

The increase of personal digital cameras with video functionality and video-enabled camera phones has increased the amount of user-generated videos on the Web. People are spending more and more time viewing online videos as a major source of entertainment and "infotainment". Social websites allow users to assign shared free-form tags to user-genera...

The rapid increase of video data on the Web has warranted an urgent need for effective representation, management and retrieval of web videos. Recently, many studies have been carried out for ontological representation of videos, either using domain dependent or generic schemas such as MPEG-7, MPEG-4, and COMM. In spite of their extensive coverage...

In this paper we discuss the use of a multimedia content model for automatic extraction of semantic metadata from multimedia content. We developed a modular and extensible framework to model the content feature of multimedia data and also describe the way it can be integrated with other existing vocabularies. The goal of this model is to generate s...

Large volumes of user-generated content on practically every major issue and event are being created on the microblogging site Twitter. This content can be combined and processed to detect events, entities and popular moods to feed various knowledge-intensive practical applications. On the downside, these content items are very noisy and highly inf...

The explosive growth of videos on the Web poses new challenges for the effective visualization of hundreds of videos at once. Given any issue-based query, a search system returns a huge list of ranked results including many different perspectives related to single issues. It would be easier for the user if the search results could be grouped based...