Temporal Variation of Terms as Concept Space for Early Risk Prediction

نویسندگان

  • Marcelo Luis Errecalde
  • Maria Paula Villegas
  • Darío Gustavo Funez
  • Maria José Garciarena Ucelay
  • Leticia Cecilia Cagnina
چکیده

Abstra t. Early risk predi tion involves three di erent aspe ts to be onsidered when an automati lassi er is implemented for this task: a) support for lassi ation with partial information read up to di erent time steps, b) support for dealing with unbalan ed data sets and ) a poli y to de ide when a do ument ould be lassi ed as belonging to the relevant lass with a reasonable on den e. In this paper we propose an approa h that naturally opes with the rst two aspe ts and shows good perspe tives to deal with the last one. Our proposal, named temporal variation of terms (TVT) is based on using the variation of vo abulary along the di erent time steps as on ept spa e to represent the do uments. Results with the eRisk 2017 data set show a better performan e of TVT in omparison to other su essful semanti analysis approa hes and the standard BOW representation. Besides, it also rea hes the best reported results up to the moment for ERDE5 and ERDE50 error evaluation measures.

برای دانلود متن کامل این مقاله و بیش از 32 میلیون مقاله دیگر ابتدا ثبت نام کنید

ثبت نام

اگر عضو سایت هستید لطفا وارد حساب کاربری خود شوید

منابع مشابه

Explaining the agency's mind in recognizing geographic space within the framework of existentialism, with emphasis on Jean-Paul Sartre's Viewpoint

In philosophy of science, particularly in the human sciences, concepts have Multiple meanings even have contradictory definition from ontological and epistemological aspects in different philosophical schools. Therefore, determination The theoretical framework for understanding of fundamental concepts, are most important in the study and understanding of the concepts in human sciences. One of t...

متن کامل

Spatio-temporal variation of wheat and silage maize water requirement using CGMS model

The Crop Growth Monitoring System (CGMS) has been applied for spatial biophysical resource analysis of Borkhar & Meymeh district in Esfahan province, Iran. The potentially suitable area for agriculture in the district has been divided into 128 homogeneous land units in terms of soil (physical characteristics), weather and administrative unit. Crop parameters required in the WOFOST simulatio...

متن کامل

Temporal Variation of Interrill Erosion Affected by Slope Gradient in Soils with Different Texture

The process of splash of soil particles by raindrops and their transport by splash or surface shallow flow is considered as interrill erosion, which can reduce soil fertility and cause pollution of surface water. This research was carried out to investigate the temporal variation of interrill erosion in different soils affected by surface slope. For this purpose, laboratory experiments were car...

متن کامل

Analysis of Hierarchical Bayesian Models for Large Space Time Data of the Housing Prices in Tehran

Housing price data is correlated to their location in different neighborhoods and their correlation is type of spatial (location). The price of housing is varius in different months, so they also have a time correlation. Spatio-temporal models are used to analyze this type of the data. An important purpose of reviewing this type of the data is to fit a suitable model for the spatial-temporal an...

متن کامل

Implementation of Green Building Concept in Commercial Buildings: Malls and Trade Center in Jakarta

Development which is less attention to the environment, inefficient use of energy as well as the increasingly dense city make space for the concept of green building to grow even more in Indonesia . The purpose of this study was to determine the extent to which the implementation of green building principles in commercial buildings. There are three buildings complexes that were examined in this...

متن کامل

ذخیره در منابع من


  با ذخیره ی این منبع در منابع من، دسترسی به آن را برای استفاده های بعدی آسان تر کنید

برای دانلود متن کامل این مقاله و بیش از 32 میلیون مقاله دیگر ابتدا ثبت نام کنید

ثبت نام

اگر عضو سایت هستید لطفا وارد حساب کاربری خود شوید

عنوان ژورنال:

دوره   شماره 

صفحات  -

تاریخ انتشار 2017