The INCOME dataset (INdonesian COMmerce and sEntiment)
Fuente:
Zenodo
Salvato in:
| Autore principale: | |
|---|---|
| Natura: | Recurso digital |
| Lingua: | indonesiano |
| Pubblicazione: |
Zenodo
2025
|
| Accesso online: | |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866902273169293312 |
|---|---|
| author | Setyorini, Dr. Haryati |
| author_facet | Setyorini, Dr. Haryati |
| contents | <h2><strong><u><span lang="EN-US">Abstract</span></u></strong></h2> <p><span lang="EN-US">The INCOME dataset (INdonesian COMmerce and sEntiment) contains 1,000 unique entries comprising e-commerce transaction records and social media posts related to digital consumption, sustainability, and support for Indonesian Micro, Small, and Medium Enterprises (MSMEs). The dataset is compiled from two primary sources: transaction logs voluntarily provided by selected Indonesian online marketplaces and publicly available user-generated content from Twitter and Instagram, collected through targeted manual searches over a defined observation period.</span></p> <p><span lang="EN-US">The transaction data (500 entries) captures product category, purchase frequency, and seller origin (local or imported), enabling analysis of consumer behavior and MSME visibility trends. Product names and marketplace identifiers are deliberately omitted to avoid any form of endorsement or marketing.</span></p> <p><span lang="EN-US">The social media data (500 entries) consists of posts manually identified and documented using hashtags such as #BeliLokal, #UMKM, and #BanggaBuatanIndonesia, enriched with authentic Indonesian slang expressions and informal writing styles common on these platforms. All data was recorded, cleaned, and validated through a manual documentation process, with no automated scraping tools used. Both original and preprocessed formats are provided, supporting research in sentiment-informed topic modeling, consumer behavior analysis, and system dynamics modeling for policy simulation.</span></p> <p><strong><u><span lang="EN-US"><span> </span></span></u></strong></p> <h2><strong><u><span lang="EN-US">Dataset Overview</span></u></strong></h2> <p><span lang="EN-US">The INCOME dataset integrates behavioral (transaction) and perceptual (social media) data to examine how public sentiment influences local MSME participation in Indonesia’s digital economy. It is designed to support research that combines Natural Language Processing (NLP) with system dynamics modeling for policy and platform strategy evaluation.</span></p> <p><span lang="EN-US">Collection was performed through a combination of direct provision from marketplace partners and manual review of public social media timelines. No automated scraping tools were used; entries were documented and cross-checked by hand to preserve accuracy, privacy, and cultural context.</span></p> <p><span lang="EN-US">In total, the dataset contains 1,000 unique entries:</span></p> <ul> <li><span lang="EN-US">500 e-commerce transaction records (250 original, 250 preprocessed)</span></li> <li><span lang="EN-US">500 social media posts (250 original, 250 preprocessed)</span></li> </ul> <p><span lang="EN-US"> </span></p> <h2><strong><u><span lang="EN-US">Contents</span></u></strong></h2> <ul> <li><strong><span lang="EN-US">/transaction_original/</span></strong></li> </ul> <p><span lang="EN-US">Contains the original e-commerce transaction logs, including product metadata, timestamps, purchase counts, and seller origin. Maintains a ~90% Imported vs ~10% Local distribution consistent with observed market dominance of imported products. Excludes actual product names and any references to marketplace-specific product origins.</span></p> <p> </p> <ul> <li><strong><span lang="EN-US">/transaction_preprocessed/</span></strong></li> </ul> <p><span lang="EN-US">Contains cleaned and standardized transaction data with normalized category names, date formats, and seller origin labels.</span></p> <p> </p> <ul> <li><strong><span lang="EN-US">/socialmedia_original/</span></strong></li> </ul> <p><span lang="EN-US">Contains raw Twitter and Instagram posts (text only) with hashtags, metadata, and Indonesian slang phrases reflective of real online discourse, including expressive punctuation, emojis, and local vernacular.</span></p> <p> </p> <ul> <li><strong><span lang="EN-US">/socialmedia_preprocessed/</span></strong></li> </ul> <p><span lang="EN-US">Contains normalized, anonymized, and tokenized versions of the social media text. Preprocessing removes emojis, strips hashtags, and preserves slang in lowercase format for analysis.</span></p> <p><strong><u><span lang="EN-US"><span> </span></span></u></strong></p> <h2><strong><u><span lang="EN-US">File Details</span></u></strong></h2> <ul> <li><strong><span lang="EN-US">/transaction_original/</span></strong></li> </ul> <p><span lang="EN-US">• Total size: ~16 KB</span></p> <p><span lang="EN-US">• Rows: 250</span></p> <p><span lang="EN-US">• Format: CSV</span></p> <p> </p> <ul> <li><strong><span lang="EN-US">/transaction_preprocessed/</span></strong></li> </ul> <p><span lang="EN-US">• Total size: ~16 KB</span></p> <p><span lang="EN-US">• Rows: 250</span></p> <p><span lang="EN-US">• Format: CSV</span></p> <p> </p> <ul> <li><strong><span lang="EN-US">/socialmedia_original/</span></strong></li> </ul> <p><span lang="EN-US">• Total size: ~19 KB</span></p> <p><span lang="EN-US">• Rows: 250</span></p> <p><span lang="EN-US">• Format: CSV</span></p> <p> </p> <ul> <li><strong><span lang="EN-US">/socialmedia_preprocessed/</span></strong></li> </ul> <p><span lang="EN-US">• Total size: ~18 KB</span></p> <p><span lang="EN-US">• Rows: 250</span></p> <p><span lang="EN-US">• Format: CSV</span></p> <p><strong><u><span lang="EN-US"><span> </span></span></u></strong></p> <h2><strong><u><span lang="EN-US">Dataset Usage</span></u></strong></h2> <p><strong><span lang="EN-US">Research Applications</span></strong></p> <p><span lang="EN-US">This dataset is ideal for:</span></p> <ul> <li><span lang="EN-US">Sentiment-informed topic modeling in Indonesian, including slang and informal speech.</span></li> <li><span lang="EN-US">Consumer behavior analysis in e-commerce ecosystems.</span></li> <li><span lang="EN-US">MSME visibility studies in platform algorithms.</span></li> <li><span lang="EN-US">Policy simulation using system dynamics.</span></li> </ul> <p><strong><span lang="EN-US">Loading and Accessing the Data</span></strong></p> <ul> <li><span lang="EN-US">Transaction data can be loaded using pandas or other tabular data libraries.</span></li> <li><span lang="EN-US">Social media text can be processed using NLP libraries such as nltk, spaCy, or transformers.</span></li> </ul> <p><strong><u><span lang="EN-US"><span> </span></span></u></strong></p> <h2><strong><u><span lang="EN-US">Preprocessing Notes</span></u></strong></h2> <p><strong><span lang="EN-US">Transaction Data</span></strong><span lang="EN-US">:</span></p> <ul> <li><span lang="EN-US">Standardized date formats, normalized category names, and unified seller origin labels.</span></li> <li><span lang="EN-US">Deduplication of repeated transaction entries.</span></li> <li><span lang="EN-US">Exclusion of marketplace-specific product names and product origin references.</span></li> </ul> <p><strong><span lang="EN-US">Social Media Data</span></strong><span lang="EN-US">:</span></p> <ul> <li><span lang="EN-US">Public posts were located by searching for specific hashtags and keywords during the observation period.</span></li> <li><span lang="EN-US">Text content was copied manually from each relevant post, ensuring accurate capture of slang, repetition, and punctuation.</span></li> <li><span lang="EN-US">Usernames and identifiable metadata were removed by hand to maintain privacy.</span></li> <li><span lang="EN-US">Hashtags and emojis were removed only in the processed version, while the original version preserves the text in its authentic form.</span></li> </ul> |
| format | Recurso digital |
| id | zenodo_https___doi_org_10_5281_zenodo_16871600 |
| institution | Zenodo |
| language | ind |
| publishDate | 2025 |
| publisher | Zenodo |
| record_format | zenodo |
| spellingShingle | The INCOME dataset (INdonesian COMmerce and sEntiment) Setyorini, Dr. Haryati <h2><strong><u><span lang="EN-US">Abstract</span></u></strong></h2> <p><span lang="EN-US">The INCOME dataset (INdonesian COMmerce and sEntiment) contains 1,000 unique entries comprising e-commerce transaction records and social media posts related to digital consumption, sustainability, and support for Indonesian Micro, Small, and Medium Enterprises (MSMEs). The dataset is compiled from two primary sources: transaction logs voluntarily provided by selected Indonesian online marketplaces and publicly available user-generated content from Twitter and Instagram, collected through targeted manual searches over a defined observation period.</span></p> <p><span lang="EN-US">The transaction data (500 entries) captures product category, purchase frequency, and seller origin (local or imported), enabling analysis of consumer behavior and MSME visibility trends. Product names and marketplace identifiers are deliberately omitted to avoid any form of endorsement or marketing.</span></p> <p><span lang="EN-US">The social media data (500 entries) consists of posts manually identified and documented using hashtags such as #BeliLokal, #UMKM, and #BanggaBuatanIndonesia, enriched with authentic Indonesian slang expressions and informal writing styles common on these platforms. All data was recorded, cleaned, and validated through a manual documentation process, with no automated scraping tools used. Both original and preprocessed formats are provided, supporting research in sentiment-informed topic modeling, consumer behavior analysis, and system dynamics modeling for policy simulation.</span></p> <p><strong><u><span lang="EN-US"><span> </span></span></u></strong></p> <h2><strong><u><span lang="EN-US">Dataset Overview</span></u></strong></h2> <p><span lang="EN-US">The INCOME dataset integrates behavioral (transaction) and perceptual (social media) data to examine how public sentiment influences local MSME participation in Indonesia’s digital economy. It is designed to support research that combines Natural Language Processing (NLP) with system dynamics modeling for policy and platform strategy evaluation.</span></p> <p><span lang="EN-US">Collection was performed through a combination of direct provision from marketplace partners and manual review of public social media timelines. No automated scraping tools were used; entries were documented and cross-checked by hand to preserve accuracy, privacy, and cultural context.</span></p> <p><span lang="EN-US">In total, the dataset contains 1,000 unique entries:</span></p> <ul> <li><span lang="EN-US">500 e-commerce transaction records (250 original, 250 preprocessed)</span></li> <li><span lang="EN-US">500 social media posts (250 original, 250 preprocessed)</span></li> </ul> <p><span lang="EN-US"> </span></p> <h2><strong><u><span lang="EN-US">Contents</span></u></strong></h2> <ul> <li><strong><span lang="EN-US">/transaction_original/</span></strong></li> </ul> <p><span lang="EN-US">Contains the original e-commerce transaction logs, including product metadata, timestamps, purchase counts, and seller origin. Maintains a ~90% Imported vs ~10% Local distribution consistent with observed market dominance of imported products. Excludes actual product names and any references to marketplace-specific product origins.</span></p> <p> </p> <ul> <li><strong><span lang="EN-US">/transaction_preprocessed/</span></strong></li> </ul> <p><span lang="EN-US">Contains cleaned and standardized transaction data with normalized category names, date formats, and seller origin labels.</span></p> <p> </p> <ul> <li><strong><span lang="EN-US">/socialmedia_original/</span></strong></li> </ul> <p><span lang="EN-US">Contains raw Twitter and Instagram posts (text only) with hashtags, metadata, and Indonesian slang phrases reflective of real online discourse, including expressive punctuation, emojis, and local vernacular.</span></p> <p> </p> <ul> <li><strong><span lang="EN-US">/socialmedia_preprocessed/</span></strong></li> </ul> <p><span lang="EN-US">Contains normalized, anonymized, and tokenized versions of the social media text. Preprocessing removes emojis, strips hashtags, and preserves slang in lowercase format for analysis.</span></p> <p><strong><u><span lang="EN-US"><span> </span></span></u></strong></p> <h2><strong><u><span lang="EN-US">File Details</span></u></strong></h2> <ul> <li><strong><span lang="EN-US">/transaction_original/</span></strong></li> </ul> <p><span lang="EN-US">• Total size: ~16 KB</span></p> <p><span lang="EN-US">• Rows: 250</span></p> <p><span lang="EN-US">• Format: CSV</span></p> <p> </p> <ul> <li><strong><span lang="EN-US">/transaction_preprocessed/</span></strong></li> </ul> <p><span lang="EN-US">• Total size: ~16 KB</span></p> <p><span lang="EN-US">• Rows: 250</span></p> <p><span lang="EN-US">• Format: CSV</span></p> <p> </p> <ul> <li><strong><span lang="EN-US">/socialmedia_original/</span></strong></li> </ul> <p><span lang="EN-US">• Total size: ~19 KB</span></p> <p><span lang="EN-US">• Rows: 250</span></p> <p><span lang="EN-US">• Format: CSV</span></p> <p> </p> <ul> <li><strong><span lang="EN-US">/socialmedia_preprocessed/</span></strong></li> </ul> <p><span lang="EN-US">• Total size: ~18 KB</span></p> <p><span lang="EN-US">• Rows: 250</span></p> <p><span lang="EN-US">• Format: CSV</span></p> <p><strong><u><span lang="EN-US"><span> </span></span></u></strong></p> <h2><strong><u><span lang="EN-US">Dataset Usage</span></u></strong></h2> <p><strong><span lang="EN-US">Research Applications</span></strong></p> <p><span lang="EN-US">This dataset is ideal for:</span></p> <ul> <li><span lang="EN-US">Sentiment-informed topic modeling in Indonesian, including slang and informal speech.</span></li> <li><span lang="EN-US">Consumer behavior analysis in e-commerce ecosystems.</span></li> <li><span lang="EN-US">MSME visibility studies in platform algorithms.</span></li> <li><span lang="EN-US">Policy simulation using system dynamics.</span></li> </ul> <p><strong><span lang="EN-US">Loading and Accessing the Data</span></strong></p> <ul> <li><span lang="EN-US">Transaction data can be loaded using pandas or other tabular data libraries.</span></li> <li><span lang="EN-US">Social media text can be processed using NLP libraries such as nltk, spaCy, or transformers.</span></li> </ul> <p><strong><u><span lang="EN-US"><span> </span></span></u></strong></p> <h2><strong><u><span lang="EN-US">Preprocessing Notes</span></u></strong></h2> <p><strong><span lang="EN-US">Transaction Data</span></strong><span lang="EN-US">:</span></p> <ul> <li><span lang="EN-US">Standardized date formats, normalized category names, and unified seller origin labels.</span></li> <li><span lang="EN-US">Deduplication of repeated transaction entries.</span></li> <li><span lang="EN-US">Exclusion of marketplace-specific product names and product origin references.</span></li> </ul> <p><strong><span lang="EN-US">Social Media Data</span></strong><span lang="EN-US">:</span></p> <ul> <li><span lang="EN-US">Public posts were located by searching for specific hashtags and keywords during the observation period.</span></li> <li><span lang="EN-US">Text content was copied manually from each relevant post, ensuring accurate capture of slang, repetition, and punctuation.</span></li> <li><span lang="EN-US">Usernames and identifiable metadata were removed by hand to maintain privacy.</span></li> <li><span lang="EN-US">Hashtags and emojis were removed only in the processed version, while the original version preserves the text in its authentic form.</span></li> </ul> |
| title | The INCOME dataset (INdonesian COMmerce and sEntiment) |
| url | https://doi.org/10.5281/zenodo.16871600 |