Use of spatial data has become an important aspect of data analysis. Use of location information can provide useful insight into the dataset. Advancement of sensor technologies and improved data connectivity have made it possible to the generation of large amounts of passively generated user location data. Apart from passively generated data from users, explicit effort has been made by commercial vendors to curate large amounts of location related data such as residential histories from a variety of sources such as credit records, litigation data, driving license records etc. Such spatial data, when linked with other datasets can provide useful insights. In this dissertation, we show that spatial information of data enables us to derive useful insights in domains of text analysis and epidemiology. We investigated primarily two types of data having spatial information - text data with location information and disease related data having residential address information. We show that in the case of text data, spatial information helps us find spatially informative topics. In the case of epidemiological data, we show residential information can be used to identify high risk spatial regions. There are instances where a primary analysis is not sufficient to establish a statistically robust conclusion. For instance, in domains such as epidemiology, where a finding is not considered to be relevant unless some statistical significance is established. We proposed techniques for significant tests which can be applied to text analysis, topic modelling, and disease mapping tasks in order to establish significance of the findings. / Computer and Information Science

Contexte : La gentrification, en transformant les environnements de vie, peut avoir un impact sur le bien-être des populations. Cependant, l’exposition à la gentrification peut être vécue et mesurée de plusieurs manières. À ce jour, les mesures existantes de ladite exposition sont uniquement fondées sur des critères objectifs déterminés à l’échelle populationnelle. Pourtant, la mesure de ce phénomène au niveau individuel incluant une dimension subjective à travers notamment la perception que l’on peut en ressentir pourrait permettre de mieux rendre compte de son impact sur le bien-être subjectif. Ce mémoire vise à faire progresser la recherche dans ce domaine, en considérant trois mesures d'exposition individuelle à la gentrification à base spatio-temporelle : l’exposition ponctuelle au domicile actuel, l’exposition moyenne aux lieux d’activités non résidentiels et l’exposition historique cumulée basée sur l’historique résidentiel. Méthode : Les données de 848 participants provenant de la première vague de la branche montréalaise de l’étude longitudinale INTERACT ont été analysées. Six modèles de régression linéaire multiple ont examiné la relation entre ces trois mesures et deux indicateurs de bien-être subjectif : l’Indice de Satisfaction de la Vie (ISV) et l’Indice du Bonheur Subjectif (IBS). Résultats : L’exposition historique à la gentrification (GentriHist) était la seule mesure d’exposition à la gentrification qui était positivement corrélée à la fois à la satisfaction de la vie (B ajusté =0,825; IC à 95% = [0,779 ; 0,836]) et au bonheur subjectif (B ajusté = 0,136; IC à 95% = [0,121 à 0,140]). Par ailleurs, l’effet d’interaction du niveau de revenu dans la relation entre la gentrification historique et la satisfaction de la vie montre que dans un contexte où les personnes à revenu suffisant (ISV moyen = 7,7) ont un niveau de satisfaction supérieur aux personnes à faible revenu (ISV moyen = 6,5), l’effet positif de l’exposition prolongée à la gentrification (plus de 3ans) est plus prononcé pour les populations défavorisées (ΔISV = 0,6) que chez les plus riches (ΔISV = 0,2). Conclusion : Nos résultats suggèrent l’intérêt de faire de la GentriHist un indicateur de référence en matière de mesure d’exposition individuelle à la gentrification ; afin de mieux en apprécier le lien avec le bien-être subjectif. / Context: Gentrification, by transforming living environments, can have an impact on people's wellbeing. However, exposure to gentrification can be experienced and measured in several ways. To date, existing measures of exposure to gentrification are solely based on population criteria, ignoring the fact that measuring this phenomenon at the individual level including its perception may better demonstrate its impact on subjective well-being. We advance the field by considering three spatiotemporal-based individual gentrification exposure measures: current home, non-residential activity places and historical gentrification. Method: Survey data from 848 adults in the Montreal-arm of the INTERACT longitudinal study were analyzed. Six multiple linear regression models examined the relationship between those three measures of gentrification exposure and two subjective well-being measures: the Life Satisfaction Index (LSI) and the Subjective Happiness Index (SHI). Results: Neither current home exposure nor site exposure were associated with the two subjective well-being indexes. Historical gentrification was positively associated with both life satisfaction (adjusted B =0,825; IC 95% = [0,779; 0,836]) and subjective happiness (adjusted B = 0,136; IC 95% = [0,121; 0,140]). Moreover, the interaction effect of income level in the relationship between historical gentrification and life satisfaction shows that in a context where people with sufficient income (average ISV = 7.7) have a level of satisfaction superior to low-income people (average ISV = 6.5), the positive effect of prolonged exposure to gentrification (more than 3 years) is more pronounced in disadvantaged populations (ΔISV = 0.6) than in the richest (ΔISV = 0 ,2). Conclusion: Our results suggest the interest of making the GentriHist a reference indicator for measuring individual exposure to gentrification, in order to better appreciate the link between gentrification and subjective well-being.