residential_London_comments

'comments.csv' is a dataset of 30,393 public comments left in response to planning applications for new residential developments in London. The dataset includes comments made in response to planning applications filed between 1/1/2021 and 1/1/2025. It covers eight of Londons local authority districts: City of London, Westminster, Lambeth, Southwark, Newham, Barnet, Brent and Ealing. The dataset contains the following columns: Name dtype Description id int id generated during scraping council string The local authority district (LAD) of the planning application comment_id string The comment ID used by the LAD application_id string The planning application ID used by the LAD (sometimes referred to as planning reference) address string Comment address stance string Registered stance to planning applciation ('objects', 'support', 'neutral') data datetime The date and time the comment was left online comment_text string Freetext of the comment add_date datetime The date and time the comment was webscraped lat float Latitude extracted from the comment address using Nominatum lon float Longitude extracted from the comment address using Nominatum cleaned_comment_text string Freetext of the comment with proper nouns (names and addresses) removed lsoa_code string The LSOA code of the comment sentiment_score float The sentiment score of the free text The dataset is complete, apart from the addresses ('address', 'lat', 'lon', 'lsoa_code') which are missing for 20% of the entries. This is due to the council websites not recording the addresses of all comments. The column 'application_id' linked this dataset to the Planning London Datahub - the GLA dataset of all planning applications filed in London. This dataset is used in our analysis of NIMBY responses to planning applications - you can find out more through the GitHub repo: Bea-Taylor/nimby_nlp. The additional datasets of 'comments_with_topics.csv' and 'topic_names.csv' record the topics generated using BERTopic.