Affiliation:
1. National University of Singapore, Singapore
2. Zhejiang University, China
3. University of Michigan
Abstract
Even with simple everyday tasks like online shopping or choosing a restaurant, users are easily overwhelmed with the large number of choices available today, each with a large number of inter-related attributes. We present ExRank, an interactive interface for exploring data that helps users understand the relationship between attribute values and find interesting items in the dataset. Based on a kNN graph and a PageRank algorithm, ExRank suggests which attributes the user should look at, and how expressed choices in particular attributes affect the distribution of values in other attributes for candidate objects. It solves the problem of empty result by showing similar items and when there are too many results, it ranks the data for the user. This demo consists of 1) the description of the software architecture and the user interface 2) the logic and reason behind our solution and 3) a list of demonstration scenarios for showing to the audience.
Subject
General Earth and Planetary Sciences,Water Science and Technology,Geography, Planning and Development
Cited by
6 articles.
订阅此论文施引文献
订阅此论文施引文献，注册后可以免费订阅5篇论文的施引文献，订阅后可以查看论文全部施引文献
1. Selecting Sub-tables for Data Exploration;2023 IEEE 39th International Conference on Data Engineering (ICDE);2023-04
2. FEDEX;Proceedings of the VLDB Endowment;2022-09
3. User Group Analytics Survey and Research Opportunities;IEEE Transactions on Knowledge and Data Engineering;2020-10-01
4. A Query Path Recommendation Method Supporting Exploratory Search Based on Search Goal Shift Graphs;Communications in Computer and Information Science;2020
5. kBrowse;Proceedings of the 28th ACM International Conference on Information and Knowledge Management;2019-11-03