diff --git a/paper.bib b/paper.bib
index e56fb6e615cb09643ffec9f96fcefee95048cd0b..1d6d86794c4b0f0d0ed4f56f4a4a013326ffe253 100644
--- a/paper.bib
+++ b/paper.bib
@@ -26,4 +26,56 @@
   booktitle = {International Conference on Data Management Technologies and Applications (DATA)},
   pages = {294-301},
   doi={10.5220/0009885702940301}
-}
\ No newline at end of file
+}
+
+@article{takada2014japanese,
+  title={Japanese study on stratification, health, income, and neighborhood: study protocol and profiles of participants},
+  author={Takada, Misato and Kondo, Naoki and Hashimoto, Hideki},
+  journal={Journal of epidemiology},
+  volume={24},
+  number={4},
+  doi={10.2188/jea.JE20130084},
+  url={https://doi.org/10.2188/jea.JE20130084},
+  pages={334--344},
+  year={2014},
+  publisher={Japan Epidemiological Association}
+}
+
+@article{frank2010development,
+  title={The development of a walkability index: application to the Neighborhood Quality of Life Study},
+  author={Frank, Lawrence D and Sallis, James F and Saelens, Brian E and Leary, Lauren and Cain, Kelli and Conway, Terry L and Hess, Paul M},
+  journal={British journal of sports medicine},
+  volume={44},
+  number={13},
+  doi={10.1136/bjsm.2009.058701},
+  url={http://dx.doi.org/10.1136/bjsm.2009.058701},
+  pages={924--933},
+  year={2010},
+  publisher={British Association of Sport and Excercise Medicine}
+}
+
+@article{garau2018evaluating,
+  title={Evaluating urban quality: Indicators and assessment tools for smart sustainable cities},
+  author={Garau, Chiara and Pavan, Valentina Maria},
+  journal={Sustainability},
+  volume={10},
+  number={3},
+  pages={575},
+  doi={10.3390/su10030575},
+  url={https://doi.org/10.3390/su10030575},
+  year={2018},
+  publisher={Multidisciplinary Digital Publishing Institute}
+}
+
+@article{leong2018biodiversity,
+  title={Biodiversity and socioeconomics in the city: a review of the luxury effect},
+  author={Leong, Misha and Dunn, Robert R and Trautwein, Michelle D},
+  journal={Biology Letters},
+  volume={14},
+  number={5},
+  pages={20180082},
+  doi={10.1098/rsbl.2018.0082},
+  url={https://doi.org/10.1098/rsbl.2018.0082},
+  year={2018},
+  publisher={The Royal Society}
+}
diff --git a/paper.md b/paper.md
index 55e6cc98841663912b511d47fd4d35f3720dddba..2ddaa0a2612f4d47dd40d7ed63e51e10bcdd773e 100644
--- a/paper.md
+++ b/paper.md
@@ -27,12 +27,19 @@ bibliography: paper.bib
 
 # Introduction
 
-Finding a real estate in a new city is a real challenge. We often arrive in a city we do not know, and finding the perfect living area becomes complex. Nearby public transportation on one hand, rural landscape on the other hand, an animated neighbourhood for some, far from urban hustle and bustle for others: there are many criteria for choosing a future neighbourhood. Our tool Predihood enables to define neighbourhoods with a set of indicators and predict their environment using supervised learning.
+Neighbourhoods are a very common concept in studies from diverse domains such as health, social sciences, or biology. For instance,
+Japanese researchers investigated the relationships between social factors and health by taking into account not only behavioural risks, but also housing and neighbourhood environments [@takada2014japanese]. In a British study, authors describe how living areas have an impact on physical activities, from which they determine a walkability index at the neighbourhood level for improving future urban planning [@frank2010development].  Lastly, a survey describes the luxury effect, i.e., the impact of wealthy neighbourhoods on the surrounding biodiversity [@leong2018biodiversity]. However there is no clear definition of the neighbourhood environment.
+
+The Predihood tool fills this gap by defining neighbourhoods, their environment and their characteristics. It includes a cartographic interface for searching and displaying information about neighbourhoods. Since it may not be possible to manually define environment for all neighbourhoods, Predihood provides a configuration interface for using popular machine-learning algorithms in order to predict missing environments.
 
 # Statement of need
 
 Several projects focus on qualifying neighbourhoods using social networks. For instance, the Livehoods project defines and computes dynamics of neighbourhoods [@cranshaw2012livehoods] while the Hoodsquare project detects similar areas based on Foursquare check-ins [@zhang2013hoodsquare]. Crowd-based systems are interesting but may be biased. [DataFrance](https://datafrance.info/) is an interface that integrates data from several sources, such as indicators provided by the National Institute of Statistics ([INSEE](https://insee.fr/en/)), geographical information from the National Geographic Institute ([IGN](http://www.ign.fr/institut/activites/geoservices-ign)) and surveys from newspapers for prices (L'Express). DataFrance enables the visualization of hundreds of indicators, but makes it difficult to judge on the environment of a neighbourhood. There is no simple description of neighbourhood's environment.
 
+The Predihood tool has been currently used to measure the impact of the neighbourhood's environment when people moves in another city [@data2020].
+Indeed, it is frequent to settle in an unknown city, and finding the perfect living area becomes complex as each individual have different preferences (e.g., rural landscape, animated or quiet location, close from public transportation). 
+However, Predihood can be extended to other application domains: measuring the pollution degree in neighbourhoods, determining whether a neighbourhood is suitable as stopover for migratory birds, etc.
+
 # Methodology
 
 In order to describe in the most accurate way the environment of a neighbourhood, social science researchers have defined six environment variables, each with a limited number of values [@data2020]. These six variables are the _building type_, the _building usage_, the _landscape_, the _social class_, the _morphological position_ and the _geographical position_. As an example, the _landscape_ can be evaluated as _urban_, _green areas_, _forest_ or _countryside_ while the _social class_ have values from _lower_ to _upper_. These variables are commonly accepted and easily understandable.