To begin mapping my data, I truncated the GEOIDs we have from the block level to the tract level, to better use the available data. I then created a new variable, tractlistings, to count the total number of listings per tract. I wanted to get a sense of how representative the dataset is, so I … More How Comprehensive is Craigslist data>

I have been analyzing the Google Places data to measure the Quality of Life score for different census tracts in the Boston area. Defining Quality of Life: The Quality of Life in a neighbourhood is a reflection of different aspects like:  Residential: Number of housing units, area of parcels, age of the construction, population … More Making maps – latent variables from Google Places

Open Street Maps : Jenna Vasington Following up on my work from last week I was interested in mapping Boston neighborhoods by percentage of activity (Individual or Institutional) in the Open Street Maps dataset. To do this I took my new aggregated dataset and mapped the percentage of Institutional activity across the Boston neighborhoods. I … More Mapping Activity

Introduction Our dataset is scraped from Twitter based on tweets in the year 2018.It contains 234487 observations(rows) and 16 columns. The feature columns include tweets and information related to them like the nature of the tweet, number of media/urls/hashtags, user information. It contains tweets from January 1, 2018 until December 31, 2018. Goal For this … More Mapping the City: Twitter Data

To continue trying to identify Craigslist ads that are discriminatory, I have now created a list of words which, when describing the tenant, are problematic. I based my list off of guidelines provided by the Fair Housing Institute. The list includes descriptions of race or ethnicity, physical or mental ability, religion and other descriptions of … More Mapping Problem Ads

Introduction: In this blog, I mostly employ text mining to extract the most common words from all airbnb descriptions to get a sense of the most frequently mentioned words in their descriptions. These words would be the attributes about the AirBnB homestay that owners want to showcase which may also represent the local tourist attractions. … More Mapping the city — Airbnb

Xin 10/30/2019 Introduction: The latent construct focus on the Guests’ preference. It has two sub-components, one is Hosts’ Performance, the other is Rating. They both have multi-part manifest variables to measure. In previous work, we’ve seen there is a strong correlation between Hosts’ Performance and Rating. This week, I will continue working on the development … More Mapping the City-Airbnb

Mapping Similarity and Host Strictness Data Exploration First, I’ll need to bring in census tract shapefiles to be able to later map my aggregations at the tract level. #lookup_code(state=”MA”,county=”Suffolk”) boston_tracts <- get_acs( geography = "tract", # county subdivision variables = 'B01003_001', state = 25, county = 25, year = 2017, survey = "acs5", geometry = … More Entropy and Gatekeeping Maps

As part of this week, I had the opportunity to learn about developing maps in R which enables to provide meaningful definition to data by visualizing it through the map. For this purpose, I will merge “Open Street Maps” data provided by Boston Area Research Initiative with the google maps. To successfully display map, I … More Mapping the city

As mentioned in my last blog post, My cousin is a realtor and she recently posted about a luxury listing she was working on. In the post she wrote: “Luxury is an experience… not a price!” I immediately knew I had to incorporate that idea into the analysis of the Airbnb data that we have. … More Airbnb(oston): A map to luxury