“I Loan Because...": Understanding Motivations for Pro-Social Lending

Principal Investigator(s): View help for Principal Investigator(s) Yang Liu, University of Michigan; Roy Chen, University of Michigan; Yan Chen, University of Michigan; Qiaozhu Mei, University of Michigan; Suzy Salib, University of Michigan

Version: View help for Version V1

Name	File Type	Size	Last Modified
Liu-et-al.-2012.pdf	application/pdf	393.6 KB	04/02/2012 11:00:AM
data_kiva.csv	text/csv	8.5 MB	03/12/2018 11:49:PM
data_kiva_documentation.txt	text/plain	1.6 KB	03/12/2018 11:27:PM

Project Citation:

Liu, Yang, Chen, Roy, Chen, Yan, Mei, Qiaozhu, and Salib, Suzy. “I Loan Because...”: Understanding Motivations for Pro-Social Lending. Ann Arbor, MI: Inter-university Consortium for Political and Social Research [distributor], 2018-03-17. https://doi.org/10.3886/E101940V1

Project Description

Summary: As a new paradigm of online communities, microﬁnance sites such as Kiva.org have attracted much public attention. To understand lender motivations on Kiva, we classify the lenders’ self-stated motivations into ten categories with human coders and machine learning based classifiers. We employ text classifiers using lexical features, along with social features based on lender activity information on Kiva, to predict the categories of lender motivation statements. Although the task appears to be much more challenging than traditional topic-based categorization, our classifiers can achieve high precision in most categories. Using the results of this classiﬁcation along with Kiva teams information, we predict lending activity from lender motivation and team affiliations. Finally, we make design recommendations regarding Kiva practices which might increase pro-social lending.

Funding Sources: National Science Foundation (SES-0720943); National Science Foundation (IIS-1054199); National Science Foundation (BCS-1111019); Google Research Award

Scope of Project

Subject Terms: lending motivation; text classiﬁcation; microfinance; pro-social lending; Kiva

Geographic Coverage: Global

Collection Date(s): 9/1/2010 – 12/31/2010 (Late 2010)

Universe: Kiva.com lenders

Data Type(s): event/transaction data; other

Collection Notes: This data was downloaded from the Kiva API in late 2010. From the API, we obtained the variables: lender (lender ID), activity_level (number of loans), mem_since (date of joining Kiva), and num_teams (number of teams joined).

We also acquired the motivation statements, lender names (to determine gender), and the total loan amounts and lender ids for each loan.

Methodology

Data Source: Kiva API

Collection Mode(s): other

Unit(s) of Observation: Individual lenders

Related Publications

Download this project

Published Versions

V1 [2018-03-17]

Export Metadata

Dublin Core

DDI 2.5

Report a Problem

Found a serious problem with the data, such as disclosure risk or copyrighted content? Let us know.

This material is distributed exactly as it arrived from the data depositor. ICPSR has not checked or processed this material. Users should consult the investigator(s) if further information is desired.