Open AccessVisualizing History for Qualitative Explanation of Valuable Events using Tangled String
Author(s) -
Yukio Ohsawa,
Teruaki Hayashi
Publication year - 2015
Publication title -
procedia computer science
Language(s) - English
Resource type - Journals
SCImago Journal Rank - 0.334
H-Index - 76
ISSN - 1877-0509
DOI - 10.1016/j.procs.2015.08.178
Subject(s) - timeline , computer science , string (physics) , granularity , event (particle physics) , value (mathematics) , data science , process (computing) , quality (philosophy) , data mining , information retrieval , artificial intelligence , epistemology , machine learning , statistics , mathematics , philosophy , physics , quantum mechanics , mathematical physics , operating system
In this paper, Tangled String, a method for visualizing sequential data is summarized and exemplified for log text of histories given as timeline lists. Valuable events are detected according to the results, on the assumption that the value of an event or an item in history means the essential impact on the past trend or on the future events that can be understood by qualitative explanation. According to the results, valuable events differ for different granularity in segmenting history into subsequences of events, corresponding to our intuitive sense of the impacts of events for human decisions and actions. This paper also aims to suggest evaluation criteria about the value of events and information in general, where their quality cannot be easily replaced by quantity. Humans’ thoughts should be involved in the process of quality evaluation, so a method such as Tangled String is desired to support this process and improve efficiency
Accelerating Research
Robert Robinson Avenue,
Oxford Science Park, Oxford
OX4 4GP, United Kingdom
Address
John Eccles HouseRobert Robinson Avenue,
Oxford Science Park, Oxford
OX4 4GP, United Kingdom