@inproceedings{84c06e74633c49fb8eebefaa7987de19,
title = "The General Index of Software Engineering Papers",
abstract = "We introduce the General Index of Software Engineering Papers, a dataset of fulltext-indexed papers from the most prominent scientific venues in the field of Software Engineering. The dataset includes both complete bibliographic information and indexed n-grams (sequence of contiguous words after removal of stopwords and non-words, for a total of 577 276 382 unique n-grams in this release) with length 1 to 5 for 44 581 papers retrieved from 34 venues over the 1971-2020 period. The dataset serves use cases in the field of meta-research, allowing to introspect the output of software engineering research even when access to papers or scholarly search engines is not possible (e.g., due to contractual reasons). The dataset also contributes to making such analyses reproducible and independently verifiable, as opposed to what happens when they are conducted using 3rd-party and non-open scholarly indexing services. The dataset is available as a portable Postgres database dump and released as open data.",
keywords = "Dataset, academic publishing, fulltext index, meta-analysis, natural language processing, ngrams, software engineering",
author = "Khalil, \{Zeinab Abou\} and Stefano Zacchiroli",
note = "Publisher Copyright: {\textcopyright} 2022 ACM.; 2022 Mining Software Repositories Conference, MSR 2022 ; Conference date: 23-05-2022 Through 24-05-2022",
year = "2022",
month = oct,
day = "17",
doi = "10.1145/3524842.3528494",
language = "English",
series = "Proceedings - 2022 Mining Software Repositories Conference, MSR 2022",
publisher = "Institute of Electrical and Electronics Engineers Inc.",
pages = "98--102",
booktitle = "Proceedings - 2022 Mining Software Repositories Conference, MSR 2022",
}