Tony Lee

BOTTARI: An augmented reality mobile application to deliver personalized and location-based recommendations by continuous analysis of social media streams

In 2011, an average of three million tweets per day was posted in Seoul. Hundreds of thousands of tweets carry the live opinion of some tens of thousands of users about restaurants, bars, cafes, and many other semi-public points of interest (POIs) in the city. Trusting this collective opinion to be a solid base for novel commercial and social services, we conceived BOTTARI: an augmented reality application that offers personalized and localized recommendation of POIs based on the temporally weighted opinions of the social media community. In this paper, we present the design of BOTTARI, the potentialities of semantic technologies such as inductive and deductive stream reasoning, and the lessons learnt in experimentally deploying BOTTARI in Insadong-a popular tourist area in Seoul-for which we have been collecting tweets for three years to rate the hundreds of restaurants in the district. The results of our study demonstrate the feasibility of BOTTARI and encourage its commercial spread.

DataGraft: One-stop-shop for open data management

This paper introduces DataGraft (https://datagraft.net/) – a cloud-based platform for data transformation and publishing. DataGraft was developed to provide better and easier to use tools for data workers and developers (e.g. open data publishers, linked data developers, data scientists) who consider existing approaches to data transformation, hosting, and access too costly and technically complex. DataGraft offers an integrated, flexible, and reliable cloud-based solution for hosted open data management. Key features include flexible management of data transformations (e.g. interactive creation, execution, sharing, reuse) and reliable data hosting services. This paper provides an overview of DataGraft focusing on the rationale, key features and components, and evaluation.

Towards BOTTARI: using stream reasoning to make sense of location-based micro-posts

Consider an urban environment and its semi-public realms (e.g., shops, bars, visitors attractions, means of transportation). Who is the maven of a district? How fast and how broad can such maven influence the opinions of others? These are just few of the questions BOTTARI (our Location-based Social Media Analysis mobile app) is getting ready to answer. In this position paper, we recap our investigation on deductive and inductive stream reasoning for social media analysis, and we show how the results of this research form the underpinning of BOTTARI.

Reality mining on micropost streams - Deductive and inductive reasoning for personalized and location-based recommendations

The rapid growth of personal opinions published in form of microposts, such as those found on Twitter, is the basis of novel emerging social and commercial services. In this paper, we describe BOTTARI, an augmented reality application that permits the personalized and localized recommendation of points of interest (POIs) based on the temporally-weighted opinions of the community. The technological basis of BOTTARI is the highly scalable LarKC platform for the rapid prototyping and development of Semantic Web applications. In particular, BOTTARI exploits LarKCs deductive and inductive stream reasoning. We present an evaluation of BOTTARI based on a three year collection of tweets about 319 restaurants located in the 2 km 2 district of Insadong, a popular tourist area of the South Korean city of Seoul. BOTTARI is the winner of the 9th edition of the Semantic Web Challenge, co-located with the 2011 International Semantic Web Conference. BOTTARI is currently field tested in Korea by Saltlux.

Location-Based Mobile Recommendations by Hybrid Reasoning on Social Media Streams

In this paper, we introduce BOTTARI: an augmented reality application that offers personalized and location-based recommendations of Point Of Interests based on sentiment analysis with geo-semantic query and reasoning. We present a mobile recommendation platform and application working on semantic technologies knowledge representation and query for geo-social data, and inductive and deductive stream reasoning, and the lesson learned in deploying BOTTARI in Insadong. We have been collecting and analyzing tweets for three years to rate the few hundreds of restaurants in the district. The results of our study show the commercial feasibility of BOTTARI.