Sanjaya Wijeratne

PhD Student @ Kno.e.sis Center

R. M. Wattegedara Sanjaya Wijeratne is a PhD student at the Computer Science Department of Wright State University. He is currently attached to Semantic Web Lab at Kno.e.sis Center and advised by Prof. Amith Sheth. His research is focused on Emoji Understanding, Emoji Sense Disambiguation, Word Sense Disambiguation and Natural Language Processing. Before moving to USA, he studied at the Faculty of Information Technology - University of Moratuwa, Sri Lanka for his bachelors in Information Technology where he obtained a first class honors, becoming the top of the class and winning the gold medal for the best GPA obtained by an undergraduate student of the Faculty of Information Technology - University of Moratuwa. Read more about his interests here at his personal Web blog, where he writes about his technical experience and a latest copy of his resume is available here for download.

Current Projects

  • EmojiNet and Emoji Understanding
    2016 July - Present

    Emoji is a contemporary, extremely popular way to enhance electronic communications. Without rigid semantics attached to them, an emoji symbol can take on different meanings based on the context of a message. Analogous to the word sense disambiguation task in natural language processing, machines also need to disambiguate the meaning of an emoji or ‘sense’ of an emoji. The goal of this project is to build tools and algorithms to improve machine understanbability of emoji. We built the first machine readable sense inventory for emoji called EmojiNet (demo). See publications related to this project at [SocInfo '16].

  • Understanding Gang Activities in Social Media
    2014 September - Present

    In this project, we try to understand how street gang members (self identified in their Twitter profiles) use social media. We try to develop algorithms to identify gang member Twitter profiles automatically using the language they use in social media posts, using the profile descriptions and/or their follower/followee networks. Read more about this in our related project page: Project Safe Neighborhood - Westwood Partnership to Prevent Juvenile Repeat Offenders. See publications related to this project at [ASONAM '16] | [SML@IJCAI '16] | [WSU Big Data '16] | [IEEE ISI '15].

Past Projects

  • eDrugTrends
    2014 September - 2015 December

    The ultimate goal of this project is to decrease the burden of psychoactive substance use in the United States by developing an innovative software platform capable of semi-automated processing of social media data to identify emerging trends in cannabis and synthetic cannabinoid use in the USA. My contributions lie in data pre-processing and filtering where I study how to employ Word Sense Disambiguation techniques to filter noisy tweets collected using highly ambiguous tweet collecting keywords. To read more about this project please visit this link. See publications related to this project at [DAD Journal '15] | [CPDD '15] | [INSIGHT '14].

  • Continuous Semantics for Crawling Events
    2013 December - 2014 April

    Twitter has become one of the major platforms that people would go to when it comes to air their opinions on various topics such as natural disasters and politics. Moreover, it has become the platform of choice for first responders to disseminate information in disaster situations and different socially and politically active groups to communicate among themselves to carry out their campaigns, making Twitter a tool that can be used to track real world events. In this project, we investigate how we can leverage Background Knowledge-bases to track evolution of events with the help of Twitter hashtags. To read more about this project please visit the project page.

  • Temporal Entity Ranking in Evolving Events
    2013 May - 2013 December

    Entities (People, Places, Organizations etc.) associated with evolving events (Hurricane Sandy, US Election 2012 etc.) has a dynamic evolution with the changing nature of events. Here, we study how to rank such entities based on their importance varying over time.

  • Linked Open Data Property Alignment
    2012 April - 2013 April

    Ontology Property Alignment is a fundamental problem in Ontology Alignment research. Here the focus is on studying schema independent approaches to identify and align properties (relationships) appear in different datasets published in Linked Open Data Cloud. For more details about this project, please see our publication at [iSemantics '13].

  • Kino Web
    2011 August - 2012 March

    A browser plugin to semantically annotate the content of a Web page using Schema.org vocabularies. Kino Web tool acts as a search engine and index all documents it accepts via a special interface and search them using semantic annotations added based on Schema.org vocabularies. Read more about Kino architecture here. For more details about this project, please see our publication at [W3C Workshp '11].

Invited Talks

  • 2016

    "Finding Street Gang Members on Twitter", Big Data Surveillance Analytics Mini Conference at Wright State University, Dayton, OH, USA. July, 2016. [Slides Share] | [Slides]

Publications

  • 2016

    Sanjaya Wijeratne, Lakshika Balasuriya, Amit Sheth, Derek Doran. EmojiNet: Building a Machine Readable Sense Inventory for Emoji. In 8th International Conference on Social Informatics (SocInfo 2016). Bellevue, WA, USA; 2016. [Kno.e.sis Library Page] | [PDF] | [DEMO]

    Sanjaya Wijeratne, Lakshika Balasuriya, Derek Doran, Amit Sheth. Word Embeddings to Enhance Twitter Gang Member Profile Identification. In IJCAI Workshop on Semantic Machine Learning (SML 2016). New York City, NY: CEUR-WS; 2016. [Kno.e.sis Library Page] | [PDF] | [Slides Share] | [Slides]

    Lakshika Balasuriya, Sanjaya Wijeratne, Derek Doran, Amit Sheth. Finding Street Gang Members on Twitter, In The 2016 IEEE/ACM International Conference on Advances in Social Networks Analysis and Mining (ASONAM 2016). San Francisco, CA, USA; 2016. [Kno.e.sis Library Page] | [PDF] | [Slides Share] | [Slides]

  • 2015

    Raminta Daniulaityte, Ramzi W. Nahhas, Sanjaya Wijeratne, Robert G. Carlson, Francois R. Lamy, Silvia S. Martins, Edward W. Boyer, G. Alan Smith, Amit Sheth, “Time for dabs”: Analyzing Twitter data on marijuana concentrates across the U.S., Drug and Alcohol Dependence, Volume 155, 1 October 2015, Pages 307-311, ISSN 0376-8716. [Kno.e.sis Library Page] | [PDF]

    Wijeratne, S.; Doran, D.; Sheth, A.; Dustin, J.L., "Analyzing the social media footprint of street gangs," in Intelligence and Security Informatics (ISI), 2015 IEEE International Conference on , vol., no., pp.91-96, 27-29 May 2015 doi: 10.1109/ISI.2015.7165945. [Kno.e.sis Library Page] | [PDF] | [Poster] | [Slides Share] | [Slides]

    R. Daniulaityte, R. Carlson, F. Golroo, S. Wijeratne, E. Boyer, S. Martins, R. Nahhas, A. Sheth, “Time for dabs”: Analyzing Twitter data on butane hash oil use. The College on Problems of Drug Dependence CPDD 2015, Phoenix, Arizona, June 13-18, 2015 (Conference Poster). [Kno.e.sis Library Page] | [PDF]

  • 2014

    Sanjaya Wijeratne, Bahareh R. Heravi. A Keyword Sense Disambiguation Based Approach for Noise Filtering in Twitter. The 1st Insight Student Conference, University College Dublin, Ireland, 2014. [Kno.e.sis Library Page] | [PDF] | [Poster]

  • 2013

    Kalpa Gunaratna, Krishnaprasad Thirunarayan, Prateek Jain, Amit Sheth, Sanjaya Wijeratne, A Statistical and Schema Independent Approach for Identifying Equivalent Properties on Linked Data. In: Proc. 9th International Conference on Semantic Systems (ACM 2013), Messe Graz, Austria, 2013. [Kno.e.sis Library Page] | [PDF] | [Slides]

  • 2011

    Ajith Ranabahu, Amit Sheth, Maryam Panahiazar, Sanjaya Wijeratne, Semantic Annotation and Search for resources in the next Generation Web with SA-REST. W3C Workshop on Data and Services Integration, October 20-21 2011, Bedford, MA, USA. [Kno.e.sis Library Page] | [PDF] | [Slides]

Research Experience

Awards & Honors

| © Sanjaya Wijeratne. Last Updated on August 2016.

| | | |