SlideShare a Scribd company logo
1 of 2
Download to read offline
www.unglobalpulse.org • info@unglobalpulse.org • 2014 1
NOWCASTING FOOD PRICES IN INDONESIA
USING SOCIAL MEDIA SIGNALS
PARTNERS: UN WORLD FOOD PROGRAMME, INDONESIA MINISTRY OF DEVELOPMENT
PLANNING (BAPPENAS), KOREA ADVANCED INSTITUTE OF SCIENCE & TECHNOLOGY
PROGRAMME AREA: FOOD & AGRICULTURE
BACKGROUND
The ability to monitor market commodity prices in real-time could
provide critical information for policy decisions on food security
and other economic issues. However, not all countries have well-
established systems for accessing and monitoring price data,
especially at a high frequency. New approaches in price
monitoring could help to fill this data gap in developing economies.
Pulse Lab Jakarta conducted a study to explore Twitter as a data
source for building a real-time food price tracking model in
Indonesia. Indonesia was chosen as the case study country for two
primary reasons. First, official commodity price data is available on
a daily or weekly basis, as the Indonesian government already uses
a dependable monitoring system for commodity prices. The
Ministry of Trade collects and publishes daily price information,
and the Indonesian Bureau of Statistics (BPS) collects weekly
commodity price information. Second, Indonesia is one of most-
tweeting countries, both in terms of number of Twitter users and
amount of generated content.
USING TWEETS TO MODEL FOOD PRICES
To refine the scope of the research study, four food commodities
(beef, chicken, onion and chili) were selected to track. These
commodities were chosen based on data availability and the
country-level priorities for food security monitoring in consultation
with the Ministry of National Development Planning and World
Food Programme (WFP) Indonesia. Data was analysed from June
2012 to September 2013, a timeframe of 15 months.
In order to extract prices as quoted on social media, a taxonomy of
keywords and phrases related to the four food commodities was
used to extract relevant public tweets, which were filtered further
for those tweets containing price quotes. Here is an example tweet
in both Bahasa and English that mentions a food price:
Pemerintah lagi sibuk! RT @promoasyik: Capai Rp 100 Ribu
per Kg, Harga Cabai Rawit Merah Setara Daging http://bit.ly/1pUmUmo
The government was busy! RT @promoasyik: Reaching Rp 100 thousand
per kg, red chili is equivalent to the price of meat http://bit.ly/1pUmUmo
A numerical filter was then used such to ensure the tweet price did
not exceed a maximum allowable daily percentage price change
(itself based on historical rates). This filter was validated through
an examination of the historical series of official food prices (for
example, a daily change of 3.5% was the largest change observed
in the beef price dataset). The numerical model was also adapted
to consider both the daily number of tweets and the divergence of
prices reported in tweets from the last official price.
Using the keyword and numerical filters to extract 41,761 relevant
tweets, a statistical model was then built in which the proxy for
daily commodity price was based on data including:
• Model price from the day before, as quoted on Twitter
• Volume of tweets (higher volumes of price quotes would make
these quotes more credible)
• Maximum daily price change rate
This nowcasting model was compared with official food prices,
aggregated daily across Indonesia. ‘Ground truth’ price data
provided by the Ministry of Trade was aggregated across the entire
country on a daily basis.
INSIGHTS & OUTCOMES
The model for nowcasting commodity prices gave high correlation
with official food price statistics over the timeframe covered.
The results of the model are shown in the table below:
COMMODITY PEARSON CORRELATION COEFFICIENT
Beef 0.87
Chicken 0.81
Onion 0.85
Chili 0.76
The research findings led to development of a near real-time food
price index to extract daily food prices from public tweets.
HOW TO CITE THIS DOCUMENT:
UN Global Pulse, 'Nowcasting Food prices in Indonesia using
Social Media Signals', Global Pulse Project Series no. 1, 2014.
SUMMARY
This project explored how Twitter data can be used to ‘nowcast’ or provide real-time food prices. Pulse Lab Jakarta collaborated with
Bappenas and WFP on the study, the outcome of which was a statistical model of daily price indicators for four food commodities:
beef, chicken, onion and chili. When the modeled prices were compared with official food prices, the figures were closely correlated,
demonstrating that near real-time social media signals can function as a proxy for daily food price statistics. This preliminary study
paves the way for further research on how social media analytics can complement traditional price data collection by offering a faster,
more affordable and efficient way of collecting real-time food prices.
www.unglobalpulse.org • info@unglobalpulse.org • 2014 2
The following four graphs show the official commodity price (in
red) compared with the statistical nowcasted price (in blue) from
July 2012 to October 2013.
BEEF: The official beef price was relatively stable for the timeframe
analysed, and the long-term price trend was accurately modeled
(nowcasted prices remained close to real prices throughout the
timeframe).
14,473 tweets contained price quotes on beef.
CHICKEN: The tool successfully modeled the price of chicken
(“daging ayam”) with significant correlation for the duration.
5,223 tweets contained price quotes on chicken.
ONION: Onion (“bawang”) fluctuated the most of the four
commodities. The model effectively tracked price variation around
April 2013, but due to the low number of tweets containing price
quotes in August did not provide a successful price proxy.
1,954 tweets contained price quotes on onions.
CHILI: Chili (“daging sapi”) showed significant price correlation,
although the proportion of relevant tweet data was much lower
than the other three commodities analysed.
1,772 tweets contained price quotes on chili.
CONCLUSIONS
This study showed that Indonesians do tweet about food prices,
and that those prices closely approximate official figures. A near
real-time food price index, with prices nowcasted using social
media signals, is an efficient tool with immediate utility for
policymaking and economic risk management.
• The study proved the potential accuracy of nowcasting by
comparing prices extracted from public tweets with official
market prices.
• This tool could provide early warning for unexpected price
spikes at much lower costs than traditional data collection.
• The simple and replicable technical needs and methodology—
keyword taxonomy refined by numerical filters—allows for
straightforward operational implementation and scaling.
The nowcasting model could potentially be adapted to other types
of commodities beyond the four food commodities analysed, or
used in other languages and countries. More complex analysis
methodologies to extract the information from the messages could
be developed (eg. based on natural language processing) to
improve the accuracy of the model. Finer-grained official price
statistics would be necessary to conduct and validate a more
detailed analysis (for example, by analysing price by location using
social media geolocation techniques).
IMPLICATIONS & RECOMMENDATIONS
• This research shows the potential for nowcasting food
commodity prices by extracting daily food prices from
public tweets to generate a near real-time food price index.
• The model prices correlated closely with official food price
statistics over the timeframe covered, demonstrating the
potential for social media signals to be used as a proxy to
model food prices.
• It is recommended this data mining approach is further
validated and applied to other commodity prices, in new
locations and using additional social data sources.
• It is recommended to develop a framework for potential
integration of near real-time indicators derived from social
data into existing national statistics agency programmes.

More Related Content

What's hot

Understanding Public Perceptions of Immunisation Using Social Media - Project...
Understanding Public Perceptions of Immunisation Using Social Media - Project...Understanding Public Perceptions of Immunisation Using Social Media - Project...
Understanding Public Perceptions of Immunisation Using Social Media - Project...UN Global Pulse
 
Analysing Seasonal Mobility Patterns Using Mobile Phone Data - Project Overview
Analysing Seasonal Mobility Patterns Using Mobile Phone Data - Project Overview Analysing Seasonal Mobility Patterns Using Mobile Phone Data - Project Overview
Analysing Seasonal Mobility Patterns Using Mobile Phone Data - Project Overview UN Global Pulse
 
Supporting the Post-2015 Development Agenda Consultations Using U-Report - Pr...
Supporting the Post-2015 Development Agenda Consultations Using U-Report - Pr...Supporting the Post-2015 Development Agenda Consultations Using U-Report - Pr...
Supporting the Post-2015 Development Agenda Consultations Using U-Report - Pr...UN Global Pulse
 
Using Mobile Phone Activity for Disaster Management During Floods - Project O...
Using Mobile Phone Activity for Disaster Management During Floods - Project O...Using Mobile Phone Activity for Disaster Management During Floods - Project O...
Using Mobile Phone Activity for Disaster Management During Floods - Project O...UN Global Pulse
 
Data Visualisation and Interactive Mapping to Support Response to Disease Out...
Data Visualisation and Interactive Mapping to Support Response to Disease Out...Data Visualisation and Interactive Mapping to Support Response to Disease Out...
Data Visualisation and Interactive Mapping to Support Response to Disease Out...UN Global Pulse
 
Supporting Forest and Peat Fire Management Using Social Media - Project Overview
Supporting Forest and Peat Fire Management Using Social Media - Project OverviewSupporting Forest and Peat Fire Management Using Social Media - Project Overview
Supporting Forest and Peat Fire Management Using Social Media - Project OverviewUN Global Pulse
 
Analyzing Attitudes Towards Contraception & Teenage Pregnancy Using Social Da...
Analyzing Attitudes Towards Contraception & Teenage Pregnancy Using Social Da...Analyzing Attitudes Towards Contraception & Teenage Pregnancy Using Social Da...
Analyzing Attitudes Towards Contraception & Teenage Pregnancy Using Social Da...UN Global Pulse
 
Mining Citizen Feedback Data for Enhanced Local Government Decision-Making - ...
Mining Citizen Feedback Data for Enhanced Local Government Decision-Making - ...Mining Citizen Feedback Data for Enhanced Local Government Decision-Making - ...
Mining Citizen Feedback Data for Enhanced Local Government Decision-Making - ...UN Global Pulse
 
Understanding Immunisation Awareness and Sentiment with Social Media - Projec...
Understanding Immunisation Awareness and Sentiment with Social Media - Projec...Understanding Immunisation Awareness and Sentiment with Social Media - Projec...
Understanding Immunisation Awareness and Sentiment with Social Media - Projec...UN Global Pulse
 
GlobalPulse_SAS_MethodsPaper2011
GlobalPulse_SAS_MethodsPaper2011GlobalPulse_SAS_MethodsPaper2011
GlobalPulse_SAS_MethodsPaper2011UN Global Pulse
 
Using Financial Transaction Data To Measure Economic Resilience To Natural Di...
Using Financial Transaction Data To Measure Economic Resilience To Natural Di...Using Financial Transaction Data To Measure Economic Resilience To Natural Di...
Using Financial Transaction Data To Measure Economic Resilience To Natural Di...UN Global Pulse
 
2015 Annual Report Pulse Lab Kampala
2015 Annual Report Pulse Lab Kampala2015 Annual Report Pulse Lab Kampala
2015 Annual Report Pulse Lab KampalaUN Global Pulse
 
Final RIVAF Report (UN Global Pulse)
Final RIVAF Report (UN Global Pulse)Final RIVAF Report (UN Global Pulse)
Final RIVAF Report (UN Global Pulse)UN Global Pulse
 
Eysenbach: Infodemiology and Infoveillance
Eysenbach: Infodemiology and InfoveillanceEysenbach: Infodemiology and Infoveillance
Eysenbach: Infodemiology and InfoveillanceGunther Eysenbach
 
Wildlife crime project overview
Wildlife crime project overviewWildlife crime project overview
Wildlife crime project overviewIIED
 
Twitter in the age of pandemics: Infodemiology and Infoveillance
Twitter in the age of pandemics: Infodemiology and InfoveillanceTwitter in the age of pandemics: Infodemiology and Infoveillance
Twitter in the age of pandemics: Infodemiology and InfoveillanceGunther Eysenbach
 
Infodemiology, Infoveillance, Twitter- and Google-based Surveillance: The Inf...
Infodemiology, Infoveillance, Twitter- and Google-based Surveillance: The Inf...Infodemiology, Infoveillance, Twitter- and Google-based Surveillance: The Inf...
Infodemiology, Infoveillance, Twitter- and Google-based Surveillance: The Inf...Gunther Eysenbach
 

What's hot (20)

Understanding Public Perceptions of Immunisation Using Social Media - Project...
Understanding Public Perceptions of Immunisation Using Social Media - Project...Understanding Public Perceptions of Immunisation Using Social Media - Project...
Understanding Public Perceptions of Immunisation Using Social Media - Project...
 
Analysing Seasonal Mobility Patterns Using Mobile Phone Data - Project Overview
Analysing Seasonal Mobility Patterns Using Mobile Phone Data - Project Overview Analysing Seasonal Mobility Patterns Using Mobile Phone Data - Project Overview
Analysing Seasonal Mobility Patterns Using Mobile Phone Data - Project Overview
 
Supporting the Post-2015 Development Agenda Consultations Using U-Report - Pr...
Supporting the Post-2015 Development Agenda Consultations Using U-Report - Pr...Supporting the Post-2015 Development Agenda Consultations Using U-Report - Pr...
Supporting the Post-2015 Development Agenda Consultations Using U-Report - Pr...
 
Using Mobile Phone Activity for Disaster Management During Floods - Project O...
Using Mobile Phone Activity for Disaster Management During Floods - Project O...Using Mobile Phone Activity for Disaster Management During Floods - Project O...
Using Mobile Phone Activity for Disaster Management During Floods - Project O...
 
Data Visualisation and Interactive Mapping to Support Response to Disease Out...
Data Visualisation and Interactive Mapping to Support Response to Disease Out...Data Visualisation and Interactive Mapping to Support Response to Disease Out...
Data Visualisation and Interactive Mapping to Support Response to Disease Out...
 
Supporting Forest and Peat Fire Management Using Social Media - Project Overview
Supporting Forest and Peat Fire Management Using Social Media - Project OverviewSupporting Forest and Peat Fire Management Using Social Media - Project Overview
Supporting Forest and Peat Fire Management Using Social Media - Project Overview
 
Analyzing Attitudes Towards Contraception & Teenage Pregnancy Using Social Da...
Analyzing Attitudes Towards Contraception & Teenage Pregnancy Using Social Da...Analyzing Attitudes Towards Contraception & Teenage Pregnancy Using Social Da...
Analyzing Attitudes Towards Contraception & Teenage Pregnancy Using Social Da...
 
Mining Citizen Feedback Data for Enhanced Local Government Decision-Making - ...
Mining Citizen Feedback Data for Enhanced Local Government Decision-Making - ...Mining Citizen Feedback Data for Enhanced Local Government Decision-Making - ...
Mining Citizen Feedback Data for Enhanced Local Government Decision-Making - ...
 
Understanding Immunisation Awareness and Sentiment with Social Media - Projec...
Understanding Immunisation Awareness and Sentiment with Social Media - Projec...Understanding Immunisation Awareness and Sentiment with Social Media - Projec...
Understanding Immunisation Awareness and Sentiment with Social Media - Projec...
 
GlobalPulse_SAS_MethodsPaper2011
GlobalPulse_SAS_MethodsPaper2011GlobalPulse_SAS_MethodsPaper2011
GlobalPulse_SAS_MethodsPaper2011
 
Using Financial Transaction Data To Measure Economic Resilience To Natural Di...
Using Financial Transaction Data To Measure Economic Resilience To Natural Di...Using Financial Transaction Data To Measure Economic Resilience To Natural Di...
Using Financial Transaction Data To Measure Economic Resilience To Natural Di...
 
Big Data and the SDGs
Big Data and the SDGsBig Data and the SDGs
Big Data and the SDGs
 
2015 Annual Report Pulse Lab Kampala
2015 Annual Report Pulse Lab Kampala2015 Annual Report Pulse Lab Kampala
2015 Annual Report Pulse Lab Kampala
 
Final RIVAF Report (UN Global Pulse)
Final RIVAF Report (UN Global Pulse)Final RIVAF Report (UN Global Pulse)
Final RIVAF Report (UN Global Pulse)
 
Eysenbach: Infodemiology and Infoveillance
Eysenbach: Infodemiology and InfoveillanceEysenbach: Infodemiology and Infoveillance
Eysenbach: Infodemiology and Infoveillance
 
Practice and level of Awareness of Good Agricultural Practices among Smallhol...
Practice and level of Awareness of Good Agricultural Practices among Smallhol...Practice and level of Awareness of Good Agricultural Practices among Smallhol...
Practice and level of Awareness of Good Agricultural Practices among Smallhol...
 
Wildlife crime project overview
Wildlife crime project overviewWildlife crime project overview
Wildlife crime project overview
 
Articles Final
Articles FinalArticles Final
Articles Final
 
Twitter in the age of pandemics: Infodemiology and Infoveillance
Twitter in the age of pandemics: Infodemiology and InfoveillanceTwitter in the age of pandemics: Infodemiology and Infoveillance
Twitter in the age of pandemics: Infodemiology and Infoveillance
 
Infodemiology, Infoveillance, Twitter- and Google-based Surveillance: The Inf...
Infodemiology, Infoveillance, Twitter- and Google-based Surveillance: The Inf...Infodemiology, Infoveillance, Twitter- and Google-based Surveillance: The Inf...
Infodemiology, Infoveillance, Twitter- and Google-based Surveillance: The Inf...
 

Similar to Nowcasting Food Prices in Indonesia with Social Media - Project Overview

Forecasting Agri-food Consumption Using Web Search Engine Indices
Forecasting Agri-food Consumption Using Web Search Engine IndicesForecasting Agri-food Consumption Using Web Search Engine Indices
Forecasting Agri-food Consumption Using Web Search Engine IndicesQUESTJOURNAL
 
Online Index - Eugine Kang
Online Index - Eugine KangOnline Index - Eugine Kang
Online Index - Eugine KangEugine Kang
 
Gender, livestock and livelihood indicators
Gender, livestock and livelihood indicatorsGender, livestock and livelihood indicators
Gender, livestock and livelihood indicatorsILRI
 
Big data for official statistics @ Konferensi Big Data Indonesia 2016
Big data for official statistics @ Konferensi Big Data Indonesia 2016 Big data for official statistics @ Konferensi Big Data Indonesia 2016
Big data for official statistics @ Konferensi Big Data Indonesia 2016 Setia Pramana
 
SUPPORTING LARGE-SCALE NUTRITION ANALYSIS BASED ON DIETARY SURVEY DATA
SUPPORTING LARGE-SCALE NUTRITION ANALYSIS BASED ON DIETARY SURVEY DATASUPPORTING LARGE-SCALE NUTRITION ANALYSIS BASED ON DIETARY SURVEY DATA
SUPPORTING LARGE-SCALE NUTRITION ANALYSIS BASED ON DIETARY SURVEY DATAhiij
 
SUPPORTING LARGE-SCALE NUTRITION ANALYSIS BASED ON DIETARY SURVEY DATA
SUPPORTING LARGE-SCALE NUTRITION ANALYSIS BASED ON DIETARY SURVEY DATASUPPORTING LARGE-SCALE NUTRITION ANALYSIS BASED ON DIETARY SURVEY DATA
SUPPORTING LARGE-SCALE NUTRITION ANALYSIS BASED ON DIETARY SURVEY DATAhiij
 
SUPPORTING LARGE-SCALE NUTRITION ANALYSIS BASED ON DIETARY SURVEY DATA
SUPPORTING LARGE-SCALE NUTRITION ANALYSIS BASED ON DIETARY SURVEY DATASUPPORTING LARGE-SCALE NUTRITION ANALYSIS BASED ON DIETARY SURVEY DATA
SUPPORTING LARGE-SCALE NUTRITION ANALYSIS BASED ON DIETARY SURVEY DATAhiij
 
SUPPORTING LARGE-SCALE NUTRITION ANALYSIS BASED ON DIETARY SURVEY DATA
SUPPORTING LARGE-SCALE NUTRITION ANALYSIS BASED ON DIETARY SURVEY DATASUPPORTING LARGE-SCALE NUTRITION ANALYSIS BASED ON DIETARY SURVEY DATA
SUPPORTING LARGE-SCALE NUTRITION ANALYSIS BASED ON DIETARY SURVEY DATAhiij
 
Changes in consumer spending habits due to covid 19
Changes in consumer spending habits due to covid 19Changes in consumer spending habits due to covid 19
Changes in consumer spending habits due to covid 19Paras Lakhotra
 
Factor Affecting Customer Purchasing Decision of Poultry Product in Indonesia...
Factor Affecting Customer Purchasing Decision of Poultry Product in Indonesia...Factor Affecting Customer Purchasing Decision of Poultry Product in Indonesia...
Factor Affecting Customer Purchasing Decision of Poultry Product in Indonesia...CharlyNamaku
 
Captstone FINAL presentation
Captstone FINAL presentationCaptstone FINAL presentation
Captstone FINAL presentationRyan Blair
 
Health Technology Assessments in India
Health Technology Assessments in IndiaHealth Technology Assessments in India
Health Technology Assessments in Indiashashi sinha
 
Built environment Resources v2
Built environment Resources v2Built environment Resources v2
Built environment Resources v2Courtney Bartlett
 
Whole sale price index
Whole sale price indexWhole sale price index
Whole sale price indexGeorgeGidudu
 

Similar to Nowcasting Food Prices in Indonesia with Social Media - Project Overview (20)

Forecasting Agri-food Consumption Using Web Search Engine Indices
Forecasting Agri-food Consumption Using Web Search Engine IndicesForecasting Agri-food Consumption Using Web Search Engine Indices
Forecasting Agri-food Consumption Using Web Search Engine Indices
 
Al 13 - chapter 6
Al   13 - chapter 6Al   13 - chapter 6
Al 13 - chapter 6
 
Online Index - Eugine Kang
Online Index - Eugine KangOnline Index - Eugine Kang
Online Index - Eugine Kang
 
Gender, livestock and livelihood indicators
Gender, livestock and livelihood indicatorsGender, livestock and livelihood indicators
Gender, livestock and livelihood indicators
 
Trend Analysis of Consumer Price Index: Useful Lessons for Business Decision ...
Trend Analysis of Consumer Price Index: Useful Lessons for Business Decision ...Trend Analysis of Consumer Price Index: Useful Lessons for Business Decision ...
Trend Analysis of Consumer Price Index: Useful Lessons for Business Decision ...
 
Big data for official statistics @ Konferensi Big Data Indonesia 2016
Big data for official statistics @ Konferensi Big Data Indonesia 2016 Big data for official statistics @ Konferensi Big Data Indonesia 2016
Big data for official statistics @ Konferensi Big Data Indonesia 2016
 
SUPPORTING LARGE-SCALE NUTRITION ANALYSIS BASED ON DIETARY SURVEY DATA
SUPPORTING LARGE-SCALE NUTRITION ANALYSIS BASED ON DIETARY SURVEY DATASUPPORTING LARGE-SCALE NUTRITION ANALYSIS BASED ON DIETARY SURVEY DATA
SUPPORTING LARGE-SCALE NUTRITION ANALYSIS BASED ON DIETARY SURVEY DATA
 
SUPPORTING LARGE-SCALE NUTRITION ANALYSIS BASED ON DIETARY SURVEY DATA
SUPPORTING LARGE-SCALE NUTRITION ANALYSIS BASED ON DIETARY SURVEY DATASUPPORTING LARGE-SCALE NUTRITION ANALYSIS BASED ON DIETARY SURVEY DATA
SUPPORTING LARGE-SCALE NUTRITION ANALYSIS BASED ON DIETARY SURVEY DATA
 
SUPPORTING LARGE-SCALE NUTRITION ANALYSIS BASED ON DIETARY SURVEY DATA
SUPPORTING LARGE-SCALE NUTRITION ANALYSIS BASED ON DIETARY SURVEY DATASUPPORTING LARGE-SCALE NUTRITION ANALYSIS BASED ON DIETARY SURVEY DATA
SUPPORTING LARGE-SCALE NUTRITION ANALYSIS BASED ON DIETARY SURVEY DATA
 
SUPPORTING LARGE-SCALE NUTRITION ANALYSIS BASED ON DIETARY SURVEY DATA
SUPPORTING LARGE-SCALE NUTRITION ANALYSIS BASED ON DIETARY SURVEY DATASUPPORTING LARGE-SCALE NUTRITION ANALYSIS BASED ON DIETARY SURVEY DATA
SUPPORTING LARGE-SCALE NUTRITION ANALYSIS BASED ON DIETARY SURVEY DATA
 
Changes in consumer spending habits due to covid 19
Changes in consumer spending habits due to covid 19Changes in consumer spending habits due to covid 19
Changes in consumer spending habits due to covid 19
 
IFPRI- Public Distribution System in India, Anjani Kumar
IFPRI- Public Distribution System in India, Anjani Kumar IFPRI- Public Distribution System in India, Anjani Kumar
IFPRI- Public Distribution System in India, Anjani Kumar
 
Factor Affecting Customer Purchasing Decision of Poultry Product in Indonesia...
Factor Affecting Customer Purchasing Decision of Poultry Product in Indonesia...Factor Affecting Customer Purchasing Decision of Poultry Product in Indonesia...
Factor Affecting Customer Purchasing Decision of Poultry Product in Indonesia...
 
Prowess Case Study
Prowess Case StudyProwess Case Study
Prowess Case Study
 
Meat-sector-outcome-report_December-2014_CLP
Meat-sector-outcome-report_December-2014_CLPMeat-sector-outcome-report_December-2014_CLP
Meat-sector-outcome-report_December-2014_CLP
 
Article Critique.docx
Article Critique.docxArticle Critique.docx
Article Critique.docx
 
Captstone FINAL presentation
Captstone FINAL presentationCaptstone FINAL presentation
Captstone FINAL presentation
 
Health Technology Assessments in India
Health Technology Assessments in IndiaHealth Technology Assessments in India
Health Technology Assessments in India
 
Built environment Resources v2
Built environment Resources v2Built environment Resources v2
Built environment Resources v2
 
Whole sale price index
Whole sale price indexWhole sale price index
Whole sale price index
 

More from UN Global Pulse

Step 2: Due Diligence Questionnaire for Prospective Partners
Step 2: Due Diligence Questionnaire for Prospective PartnersStep 2: Due Diligence Questionnaire for Prospective Partners
Step 2: Due Diligence Questionnaire for Prospective PartnersUN Global Pulse
 
Step 1: Due Diligence Checklist for Prospective Partners
Step 1: Due Diligence Checklist for Prospective Partners Step 1: Due Diligence Checklist for Prospective Partners
Step 1: Due Diligence Checklist for Prospective Partners UN Global Pulse
 
Using Data and New Technology for Peacemaking, Preventive Diplomacy, and Peac...
Using Data and New Technology for Peacemaking, Preventive Diplomacy, and Peac...Using Data and New Technology for Peacemaking, Preventive Diplomacy, and Peac...
Using Data and New Technology for Peacemaking, Preventive Diplomacy, and Peac...UN Global Pulse
 
Pulse Lab Kampala Progress Report 2016/2017
Pulse Lab Kampala Progress Report 2016/2017Pulse Lab Kampala Progress Report 2016/2017
Pulse Lab Kampala Progress Report 2016/2017UN Global Pulse
 
UN Global Pulse Annual Report 2018
UN Global Pulse Annual Report 2018UN Global Pulse Annual Report 2018
UN Global Pulse Annual Report 2018UN Global Pulse
 
Pulse Lab Jakarta Annual Report 2018
Pulse Lab Jakarta Annual Report 2018 Pulse Lab Jakarta Annual Report 2018
Pulse Lab Jakarta Annual Report 2018 UN Global Pulse
 
Risks, Harms and Benefits Assessment Tool (Updated as of Jan 2019)
Risks, Harms and Benefits Assessment Tool (Updated as of Jan 2019)Risks, Harms and Benefits Assessment Tool (Updated as of Jan 2019)
Risks, Harms and Benefits Assessment Tool (Updated as of Jan 2019)UN Global Pulse
 
Pulse Lab Jakarta 2015 Annual Report
Pulse Lab Jakarta 2015 Annual Report Pulse Lab Jakarta 2015 Annual Report
Pulse Lab Jakarta 2015 Annual Report UN Global Pulse
 
Embracing Innovation: How a Social Lab can Support the Innovation Agenda in S...
Embracing Innovation: How a Social Lab can Support the Innovation Agenda in S...Embracing Innovation: How a Social Lab can Support the Innovation Agenda in S...
Embracing Innovation: How a Social Lab can Support the Innovation Agenda in S...UN Global Pulse
 
Urban Vulnerability Mapping Toolkit
Urban Vulnerability Mapping ToolkitUrban Vulnerability Mapping Toolkit
Urban Vulnerability Mapping ToolkitUN Global Pulse
 
Navigating the Terrain: A Toolkit for Conceptualising Service Design Projects
Navigating the Terrain: A Toolkit for Conceptualising Service Design ProjectsNavigating the Terrain: A Toolkit for Conceptualising Service Design Projects
Navigating the Terrain: A Toolkit for Conceptualising Service Design ProjectsUN Global Pulse
 
Experimenting with Big Data and AI to Support Peace and Security
Experimenting with Big Data and AI to Support Peace and SecurityExperimenting with Big Data and AI to Support Peace and Security
Experimenting with Big Data and AI to Support Peace and SecurityUN Global Pulse
 
Banking on Fintech: Financial inclusion for micro enterprises in Indonesia
Banking on Fintech: Financial inclusion for micro enterprises in IndonesiaBanking on Fintech: Financial inclusion for micro enterprises in Indonesia
Banking on Fintech: Financial inclusion for micro enterprises in IndonesiaUN Global Pulse
 
Haze Gazer - Tool Overview
Haze Gazer - Tool Overview Haze Gazer - Tool Overview
Haze Gazer - Tool Overview UN Global Pulse
 
Building Proxy Indicators of National Wellbeing with Postal Data - Project Ov...
Building Proxy Indicators of National Wellbeing with Postal Data - Project Ov...Building Proxy Indicators of National Wellbeing with Postal Data - Project Ov...
Building Proxy Indicators of National Wellbeing with Postal Data - Project Ov...UN Global Pulse
 
Sex Disaggregation of Social Media Posts - Tool Overview
Sex Disaggregation of Social Media Posts - Tool OverviewSex Disaggregation of Social Media Posts - Tool Overview
Sex Disaggregation of Social Media Posts - Tool OverviewUN Global Pulse
 
Using Big data Analytics for Improved Public Transport
Using Big data Analytics for Improved Public Transport Using Big data Analytics for Improved Public Transport
Using Big data Analytics for Improved Public Transport UN Global Pulse
 
Translator Gator - Tool Overview
Translator Gator - Tool Overview Translator Gator - Tool Overview
Translator Gator - Tool Overview UN Global Pulse
 
Big Data for Financial Inclusion, Examining the Customer Journey - Project Ov...
Big Data for Financial Inclusion, Examining the Customer Journey - Project Ov...Big Data for Financial Inclusion, Examining the Customer Journey - Project Ov...
Big Data for Financial Inclusion, Examining the Customer Journey - Project Ov...UN Global Pulse
 
Understanding Perceptions of Migrants and Refugees with Social Media - Projec...
Understanding Perceptions of Migrants and Refugees with Social Media - Projec...Understanding Perceptions of Migrants and Refugees with Social Media - Projec...
Understanding Perceptions of Migrants and Refugees with Social Media - Projec...UN Global Pulse
 

More from UN Global Pulse (20)

Step 2: Due Diligence Questionnaire for Prospective Partners
Step 2: Due Diligence Questionnaire for Prospective PartnersStep 2: Due Diligence Questionnaire for Prospective Partners
Step 2: Due Diligence Questionnaire for Prospective Partners
 
Step 1: Due Diligence Checklist for Prospective Partners
Step 1: Due Diligence Checklist for Prospective Partners Step 1: Due Diligence Checklist for Prospective Partners
Step 1: Due Diligence Checklist for Prospective Partners
 
Using Data and New Technology for Peacemaking, Preventive Diplomacy, and Peac...
Using Data and New Technology for Peacemaking, Preventive Diplomacy, and Peac...Using Data and New Technology for Peacemaking, Preventive Diplomacy, and Peac...
Using Data and New Technology for Peacemaking, Preventive Diplomacy, and Peac...
 
Pulse Lab Kampala Progress Report 2016/2017
Pulse Lab Kampala Progress Report 2016/2017Pulse Lab Kampala Progress Report 2016/2017
Pulse Lab Kampala Progress Report 2016/2017
 
UN Global Pulse Annual Report 2018
UN Global Pulse Annual Report 2018UN Global Pulse Annual Report 2018
UN Global Pulse Annual Report 2018
 
Pulse Lab Jakarta Annual Report 2018
Pulse Lab Jakarta Annual Report 2018 Pulse Lab Jakarta Annual Report 2018
Pulse Lab Jakarta Annual Report 2018
 
Risks, Harms and Benefits Assessment Tool (Updated as of Jan 2019)
Risks, Harms and Benefits Assessment Tool (Updated as of Jan 2019)Risks, Harms and Benefits Assessment Tool (Updated as of Jan 2019)
Risks, Harms and Benefits Assessment Tool (Updated as of Jan 2019)
 
Pulse Lab Jakarta 2015 Annual Report
Pulse Lab Jakarta 2015 Annual Report Pulse Lab Jakarta 2015 Annual Report
Pulse Lab Jakarta 2015 Annual Report
 
Embracing Innovation: How a Social Lab can Support the Innovation Agenda in S...
Embracing Innovation: How a Social Lab can Support the Innovation Agenda in S...Embracing Innovation: How a Social Lab can Support the Innovation Agenda in S...
Embracing Innovation: How a Social Lab can Support the Innovation Agenda in S...
 
Urban Vulnerability Mapping Toolkit
Urban Vulnerability Mapping ToolkitUrban Vulnerability Mapping Toolkit
Urban Vulnerability Mapping Toolkit
 
Navigating the Terrain: A Toolkit for Conceptualising Service Design Projects
Navigating the Terrain: A Toolkit for Conceptualising Service Design ProjectsNavigating the Terrain: A Toolkit for Conceptualising Service Design Projects
Navigating the Terrain: A Toolkit for Conceptualising Service Design Projects
 
Experimenting with Big Data and AI to Support Peace and Security
Experimenting with Big Data and AI to Support Peace and SecurityExperimenting with Big Data and AI to Support Peace and Security
Experimenting with Big Data and AI to Support Peace and Security
 
Banking on Fintech: Financial inclusion for micro enterprises in Indonesia
Banking on Fintech: Financial inclusion for micro enterprises in IndonesiaBanking on Fintech: Financial inclusion for micro enterprises in Indonesia
Banking on Fintech: Financial inclusion for micro enterprises in Indonesia
 
Haze Gazer - Tool Overview
Haze Gazer - Tool Overview Haze Gazer - Tool Overview
Haze Gazer - Tool Overview
 
Building Proxy Indicators of National Wellbeing with Postal Data - Project Ov...
Building Proxy Indicators of National Wellbeing with Postal Data - Project Ov...Building Proxy Indicators of National Wellbeing with Postal Data - Project Ov...
Building Proxy Indicators of National Wellbeing with Postal Data - Project Ov...
 
Sex Disaggregation of Social Media Posts - Tool Overview
Sex Disaggregation of Social Media Posts - Tool OverviewSex Disaggregation of Social Media Posts - Tool Overview
Sex Disaggregation of Social Media Posts - Tool Overview
 
Using Big data Analytics for Improved Public Transport
Using Big data Analytics for Improved Public Transport Using Big data Analytics for Improved Public Transport
Using Big data Analytics for Improved Public Transport
 
Translator Gator - Tool Overview
Translator Gator - Tool Overview Translator Gator - Tool Overview
Translator Gator - Tool Overview
 
Big Data for Financial Inclusion, Examining the Customer Journey - Project Ov...
Big Data for Financial Inclusion, Examining the Customer Journey - Project Ov...Big Data for Financial Inclusion, Examining the Customer Journey - Project Ov...
Big Data for Financial Inclusion, Examining the Customer Journey - Project Ov...
 
Understanding Perceptions of Migrants and Refugees with Social Media - Projec...
Understanding Perceptions of Migrants and Refugees with Social Media - Projec...Understanding Perceptions of Migrants and Refugees with Social Media - Projec...
Understanding Perceptions of Migrants and Refugees with Social Media - Projec...
 

Recently uploaded

Elements of language learning - an analysis of how different elements of lang...
Elements of language learning - an analysis of how different elements of lang...Elements of language learning - an analysis of how different elements of lang...
Elements of language learning - an analysis of how different elements of lang...PrithaVashisht1
 
Protein struc pred-Ab initio and other methods as a short introduction.ppt
Protein struc pred-Ab initio and other methods as a short introduction.pptProtein struc pred-Ab initio and other methods as a short introduction.ppt
Protein struc pred-Ab initio and other methods as a short introduction.ppt60BT119YAZHINIK
 
CCS336-Cloud-Services-Management-Lecture-Notes-1.pptx
CCS336-Cloud-Services-Management-Lecture-Notes-1.pptxCCS336-Cloud-Services-Management-Lecture-Notes-1.pptx
CCS336-Cloud-Services-Management-Lecture-Notes-1.pptxdhiyaneswaranv1
 
Persuasive E-commerce, Our Biased Brain @ Bikkeldag 2024
Persuasive E-commerce, Our Biased Brain @ Bikkeldag 2024Persuasive E-commerce, Our Biased Brain @ Bikkeldag 2024
Persuasive E-commerce, Our Biased Brain @ Bikkeldag 2024Guido X Jansen
 
Cement class 12 notes of cement chapter.pdf
Cement class 12 notes of cement chapter.pdfCement class 12 notes of cement chapter.pdf
Cement class 12 notes of cement chapter.pdfSafalPoudel6
 
Feast Feature Store - An In-depth Overview Experimentation and Application in...
Feast Feature Store - An In-depth Overview Experimentation and Application in...Feast Feature Store - An In-depth Overview Experimentation and Application in...
Feast Feature Store - An In-depth Overview Experimentation and Application in...Hong Ong
 
UX Edinburgh Meetup - Privacy UX - March 2024.pdf
UX Edinburgh Meetup - Privacy UX - March 2024.pdfUX Edinburgh Meetup - Privacy UX - March 2024.pdf
UX Edinburgh Meetup - Privacy UX - March 2024.pdfhello758250
 
Strategic CX: A Deep Dive into Voice of the Customer Insights for Clarity
Strategic CX: A Deep Dive into Voice of the Customer Insights for ClarityStrategic CX: A Deep Dive into Voice of the Customer Insights for Clarity
Strategic CX: A Deep Dive into Voice of the Customer Insights for ClarityAggregage
 
28March2024-Codeless-Generative-AI-Pipelines
28March2024-Codeless-Generative-AI-Pipelines28March2024-Codeless-Generative-AI-Pipelines
28March2024-Codeless-Generative-AI-PipelinesTimothy Spann
 
Transcription in living organisms- An overview.pptx
Transcription in living organisms- An overview.pptxTranscription in living organisms- An overview.pptx
Transcription in living organisms- An overview.pptxShubhrangshuHalder2
 
Appreciating how time and practice affect IELTS learners in their journey to ...
Appreciating how time and practice affect IELTS learners in their journey to ...Appreciating how time and practice affect IELTS learners in their journey to ...
Appreciating how time and practice affect IELTS learners in their journey to ...PrithaVashisht1
 
DOC-20240326-WA0008..pptx by Abhishek lal
DOC-20240326-WA0008..pptx by Abhishek lalDOC-20240326-WA0008..pptx by Abhishek lal
DOC-20240326-WA0008..pptx by Abhishek lalnikkicross391
 
Rock Songs common codes and conventions.pptx
Rock Songs common codes and conventions.pptxRock Songs common codes and conventions.pptx
Rock Songs common codes and conventions.pptxFinatron037
 
Virtuosoft SmartSync Product Introduction
Virtuosoft SmartSync Product IntroductionVirtuosoft SmartSync Product Introduction
Virtuosoft SmartSync Product Introductionsanjaymuralee1
 
Optimal Decision Making - Cost Reduction in Logistics
Optimal Decision Making - Cost Reduction in LogisticsOptimal Decision Making - Cost Reduction in Logistics
Optimal Decision Making - Cost Reduction in LogisticsThinkInnovation
 
The Universal GTM - how we design GTM and dataLayer
The Universal GTM - how we design GTM and dataLayerThe Universal GTM - how we design GTM and dataLayer
The Universal GTM - how we design GTM and dataLayerPavel Šabatka
 
Data Visualization Report For Business Analytics.docx
Data Visualization Report For Business Analytics.docxData Visualization Report For Business Analytics.docx
Data Visualization Report For Business Analytics.docxahmeds551
 
AppliedGenAI 3 days workshop_GSV_updated.pdf
AppliedGenAI 3 days workshop_GSV_updated.pdfAppliedGenAI 3 days workshop_GSV_updated.pdf
AppliedGenAI 3 days workshop_GSV_updated.pdfObjectAutomation2
 

Recently uploaded (18)

Elements of language learning - an analysis of how different elements of lang...
Elements of language learning - an analysis of how different elements of lang...Elements of language learning - an analysis of how different elements of lang...
Elements of language learning - an analysis of how different elements of lang...
 
Protein struc pred-Ab initio and other methods as a short introduction.ppt
Protein struc pred-Ab initio and other methods as a short introduction.pptProtein struc pred-Ab initio and other methods as a short introduction.ppt
Protein struc pred-Ab initio and other methods as a short introduction.ppt
 
CCS336-Cloud-Services-Management-Lecture-Notes-1.pptx
CCS336-Cloud-Services-Management-Lecture-Notes-1.pptxCCS336-Cloud-Services-Management-Lecture-Notes-1.pptx
CCS336-Cloud-Services-Management-Lecture-Notes-1.pptx
 
Persuasive E-commerce, Our Biased Brain @ Bikkeldag 2024
Persuasive E-commerce, Our Biased Brain @ Bikkeldag 2024Persuasive E-commerce, Our Biased Brain @ Bikkeldag 2024
Persuasive E-commerce, Our Biased Brain @ Bikkeldag 2024
 
Cement class 12 notes of cement chapter.pdf
Cement class 12 notes of cement chapter.pdfCement class 12 notes of cement chapter.pdf
Cement class 12 notes of cement chapter.pdf
 
Feast Feature Store - An In-depth Overview Experimentation and Application in...
Feast Feature Store - An In-depth Overview Experimentation and Application in...Feast Feature Store - An In-depth Overview Experimentation and Application in...
Feast Feature Store - An In-depth Overview Experimentation and Application in...
 
UX Edinburgh Meetup - Privacy UX - March 2024.pdf
UX Edinburgh Meetup - Privacy UX - March 2024.pdfUX Edinburgh Meetup - Privacy UX - March 2024.pdf
UX Edinburgh Meetup - Privacy UX - March 2024.pdf
 
Strategic CX: A Deep Dive into Voice of the Customer Insights for Clarity
Strategic CX: A Deep Dive into Voice of the Customer Insights for ClarityStrategic CX: A Deep Dive into Voice of the Customer Insights for Clarity
Strategic CX: A Deep Dive into Voice of the Customer Insights for Clarity
 
28March2024-Codeless-Generative-AI-Pipelines
28March2024-Codeless-Generative-AI-Pipelines28March2024-Codeless-Generative-AI-Pipelines
28March2024-Codeless-Generative-AI-Pipelines
 
Transcription in living organisms- An overview.pptx
Transcription in living organisms- An overview.pptxTranscription in living organisms- An overview.pptx
Transcription in living organisms- An overview.pptx
 
Appreciating how time and practice affect IELTS learners in their journey to ...
Appreciating how time and practice affect IELTS learners in their journey to ...Appreciating how time and practice affect IELTS learners in their journey to ...
Appreciating how time and practice affect IELTS learners in their journey to ...
 
DOC-20240326-WA0008..pptx by Abhishek lal
DOC-20240326-WA0008..pptx by Abhishek lalDOC-20240326-WA0008..pptx by Abhishek lal
DOC-20240326-WA0008..pptx by Abhishek lal
 
Rock Songs common codes and conventions.pptx
Rock Songs common codes and conventions.pptxRock Songs common codes and conventions.pptx
Rock Songs common codes and conventions.pptx
 
Virtuosoft SmartSync Product Introduction
Virtuosoft SmartSync Product IntroductionVirtuosoft SmartSync Product Introduction
Virtuosoft SmartSync Product Introduction
 
Optimal Decision Making - Cost Reduction in Logistics
Optimal Decision Making - Cost Reduction in LogisticsOptimal Decision Making - Cost Reduction in Logistics
Optimal Decision Making - Cost Reduction in Logistics
 
The Universal GTM - how we design GTM and dataLayer
The Universal GTM - how we design GTM and dataLayerThe Universal GTM - how we design GTM and dataLayer
The Universal GTM - how we design GTM and dataLayer
 
Data Visualization Report For Business Analytics.docx
Data Visualization Report For Business Analytics.docxData Visualization Report For Business Analytics.docx
Data Visualization Report For Business Analytics.docx
 
AppliedGenAI 3 days workshop_GSV_updated.pdf
AppliedGenAI 3 days workshop_GSV_updated.pdfAppliedGenAI 3 days workshop_GSV_updated.pdf
AppliedGenAI 3 days workshop_GSV_updated.pdf
 

Nowcasting Food Prices in Indonesia with Social Media - Project Overview

  • 1. www.unglobalpulse.org • info@unglobalpulse.org • 2014 1 NOWCASTING FOOD PRICES IN INDONESIA USING SOCIAL MEDIA SIGNALS PARTNERS: UN WORLD FOOD PROGRAMME, INDONESIA MINISTRY OF DEVELOPMENT PLANNING (BAPPENAS), KOREA ADVANCED INSTITUTE OF SCIENCE & TECHNOLOGY PROGRAMME AREA: FOOD & AGRICULTURE BACKGROUND The ability to monitor market commodity prices in real-time could provide critical information for policy decisions on food security and other economic issues. However, not all countries have well- established systems for accessing and monitoring price data, especially at a high frequency. New approaches in price monitoring could help to fill this data gap in developing economies. Pulse Lab Jakarta conducted a study to explore Twitter as a data source for building a real-time food price tracking model in Indonesia. Indonesia was chosen as the case study country for two primary reasons. First, official commodity price data is available on a daily or weekly basis, as the Indonesian government already uses a dependable monitoring system for commodity prices. The Ministry of Trade collects and publishes daily price information, and the Indonesian Bureau of Statistics (BPS) collects weekly commodity price information. Second, Indonesia is one of most- tweeting countries, both in terms of number of Twitter users and amount of generated content. USING TWEETS TO MODEL FOOD PRICES To refine the scope of the research study, four food commodities (beef, chicken, onion and chili) were selected to track. These commodities were chosen based on data availability and the country-level priorities for food security monitoring in consultation with the Ministry of National Development Planning and World Food Programme (WFP) Indonesia. Data was analysed from June 2012 to September 2013, a timeframe of 15 months. In order to extract prices as quoted on social media, a taxonomy of keywords and phrases related to the four food commodities was used to extract relevant public tweets, which were filtered further for those tweets containing price quotes. Here is an example tweet in both Bahasa and English that mentions a food price: Pemerintah lagi sibuk! RT @promoasyik: Capai Rp 100 Ribu per Kg, Harga Cabai Rawit Merah Setara Daging http://bit.ly/1pUmUmo The government was busy! RT @promoasyik: Reaching Rp 100 thousand per kg, red chili is equivalent to the price of meat http://bit.ly/1pUmUmo A numerical filter was then used such to ensure the tweet price did not exceed a maximum allowable daily percentage price change (itself based on historical rates). This filter was validated through an examination of the historical series of official food prices (for example, a daily change of 3.5% was the largest change observed in the beef price dataset). The numerical model was also adapted to consider both the daily number of tweets and the divergence of prices reported in tweets from the last official price. Using the keyword and numerical filters to extract 41,761 relevant tweets, a statistical model was then built in which the proxy for daily commodity price was based on data including: • Model price from the day before, as quoted on Twitter • Volume of tweets (higher volumes of price quotes would make these quotes more credible) • Maximum daily price change rate This nowcasting model was compared with official food prices, aggregated daily across Indonesia. ‘Ground truth’ price data provided by the Ministry of Trade was aggregated across the entire country on a daily basis. INSIGHTS & OUTCOMES The model for nowcasting commodity prices gave high correlation with official food price statistics over the timeframe covered. The results of the model are shown in the table below: COMMODITY PEARSON CORRELATION COEFFICIENT Beef 0.87 Chicken 0.81 Onion 0.85 Chili 0.76 The research findings led to development of a near real-time food price index to extract daily food prices from public tweets. HOW TO CITE THIS DOCUMENT: UN Global Pulse, 'Nowcasting Food prices in Indonesia using Social Media Signals', Global Pulse Project Series no. 1, 2014. SUMMARY This project explored how Twitter data can be used to ‘nowcast’ or provide real-time food prices. Pulse Lab Jakarta collaborated with Bappenas and WFP on the study, the outcome of which was a statistical model of daily price indicators for four food commodities: beef, chicken, onion and chili. When the modeled prices were compared with official food prices, the figures were closely correlated, demonstrating that near real-time social media signals can function as a proxy for daily food price statistics. This preliminary study paves the way for further research on how social media analytics can complement traditional price data collection by offering a faster, more affordable and efficient way of collecting real-time food prices.
  • 2. www.unglobalpulse.org • info@unglobalpulse.org • 2014 2 The following four graphs show the official commodity price (in red) compared with the statistical nowcasted price (in blue) from July 2012 to October 2013. BEEF: The official beef price was relatively stable for the timeframe analysed, and the long-term price trend was accurately modeled (nowcasted prices remained close to real prices throughout the timeframe). 14,473 tweets contained price quotes on beef. CHICKEN: The tool successfully modeled the price of chicken (“daging ayam”) with significant correlation for the duration. 5,223 tweets contained price quotes on chicken. ONION: Onion (“bawang”) fluctuated the most of the four commodities. The model effectively tracked price variation around April 2013, but due to the low number of tweets containing price quotes in August did not provide a successful price proxy. 1,954 tweets contained price quotes on onions. CHILI: Chili (“daging sapi”) showed significant price correlation, although the proportion of relevant tweet data was much lower than the other three commodities analysed. 1,772 tweets contained price quotes on chili. CONCLUSIONS This study showed that Indonesians do tweet about food prices, and that those prices closely approximate official figures. A near real-time food price index, with prices nowcasted using social media signals, is an efficient tool with immediate utility for policymaking and economic risk management. • The study proved the potential accuracy of nowcasting by comparing prices extracted from public tweets with official market prices. • This tool could provide early warning for unexpected price spikes at much lower costs than traditional data collection. • The simple and replicable technical needs and methodology— keyword taxonomy refined by numerical filters—allows for straightforward operational implementation and scaling. The nowcasting model could potentially be adapted to other types of commodities beyond the four food commodities analysed, or used in other languages and countries. More complex analysis methodologies to extract the information from the messages could be developed (eg. based on natural language processing) to improve the accuracy of the model. Finer-grained official price statistics would be necessary to conduct and validate a more detailed analysis (for example, by analysing price by location using social media geolocation techniques). IMPLICATIONS & RECOMMENDATIONS • This research shows the potential for nowcasting food commodity prices by extracting daily food prices from public tweets to generate a near real-time food price index. • The model prices correlated closely with official food price statistics over the timeframe covered, demonstrating the potential for social media signals to be used as a proxy to model food prices. • It is recommended this data mining approach is further validated and applied to other commodity prices, in new locations and using additional social data sources. • It is recommended to develop a framework for potential integration of near real-time indicators derived from social data into existing national statistics agency programmes.