{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,6,18]],"date-time":"2025-06-18T04:33:54Z","timestamp":1750221234448,"version":"3.41.0"},"publisher-location":"New York, NY, USA","reference-count":36,"publisher":"ACM","license":[{"start":{"date-parts":[[2018,7,22]],"date-time":"2018-07-22T00:00:00Z","timestamp":1532217600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.acm.org\/publications\/policies\/copyright_policy#Background"}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2018,7,22]]},"DOI":"10.1145\/3219104.3219153","type":"proceedings-article","created":{"date-parts":[[2018,7,12]],"date-time":"2018-07-12T17:46:44Z","timestamp":1531417604000},"page":"1-8","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["A Computational Notebook Approach to Large-scale Text Analysis"],"prefix":"10.1145","author":[{"given":"Guangchen","family":"Ruan","sequence":"first","affiliation":[{"name":"Pervasive Technology Institute, Indiana University"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Tassie","family":"Gniady","sequence":"additional","affiliation":[{"name":"Pervasive Technology Institute, Indiana University"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"David","family":"Kloster","sequence":"additional","affiliation":[{"name":"Pervasive Technology Institute, Indiana University"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Eric","family":"Wernert","sequence":"additional","affiliation":[{"name":"Pervasive Technology Institute, Indiana University"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Esen","family":"Tuna","sequence":"additional","affiliation":[{"name":"Pervasive Technology Institute, Indiana University"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"320","published-online":{"date-parts":[[2018,7,22]]},"reference":[{"key":"e_1_3_2_1_1_1","doi-asserted-by":"publisher","DOI":"10.1109\/VAST.2014.7042493"},{"key":"e_1_3_2_1_2_1","volume-title":"Retrieved","author":"HathiTrust Research Center Analytics.","year":"2018","unstructured":"HathiTrust Research Center Analytics. 2018 . HathiTrust Research Center Analytics Homepage. (Feb. 2018) . Retrieved Feb 13, 2018 from https:\/\/analytics.hathitrust.org\/ HathiTrust Research Center Analytics. 2018. HathiTrust Research Center Analytics Homepage. (Feb. 2018). Retrieved Feb 13, 2018 from https:\/\/analytics.hathitrust.org\/"},{"key":"e_1_3_2_1_3_1","volume-title":"Retrieved","author":"Filesystem Architecture Hadoop Distributed","year":"2018","unstructured":"Hadoop Distributed Filesystem Architecture . 2018 . Hadoop Distributed Filesystem Homepage. (Feb. 2018) . Retrieved Feb 13, 2018 from https:\/\/hadoop.apache.org\/docs\/r1.2.1\/hdfs_design.html Hadoop Distributed Filesystem Architecture. 2018. Hadoop Distributed Filesystem Homepage. (Feb. 2018). Retrieved Feb 13, 2018 from https:\/\/hadoop.apache.org\/docs\/r1.2.1\/hdfs_design.html"},{"key":"e_1_3_2_1_4_1","article-title":"Latent Dirichlet Allocation","author":"Blei David M.","year":"2003","unstructured":"David M. Blei , Andrew Y. Ng , and Michael I. Jordan . 2003 . Latent Dirichlet Allocation . Journal of Machine Learning Research 3 ( Jan. 2003), 993--1022. David M. Blei, Andrew Y. Ng, and Michael I. Jordan. 2003. Latent Dirichlet Allocation. Journal of Machine Learning Research 3 (Jan. 2003), 993--1022.","journal-title":"Journal of Machine Learning Research 3"},{"key":"e_1_3_2_1_5_1","doi-asserted-by":"crossref","unstructured":"LM Aiello etal CA Davis GL Ciampaglia. {n. d.}. OSoMe: the IUNI observatory on social media. Peerj Computer Science 2:e87 ({n. d.}).  LM Aiello et al. CA Davis GL Ciampaglia. {n. d.}. OSoMe: the IUNI observatory on social media. Peerj Computer Science 2:e87 ({n. d.}).","DOI":"10.7717\/peerj-cs.87"},{"key":"e_1_3_2_1_6_1","volume-title":"Retrieved","author":"HathiTrust Research Center","year":"2018","unstructured":"HathiTrust Research Center . 2018 . HathiTrust Research Center Homepage. (Feb. 2018) . Retrieved Feb 13, 2018 from https:\/\/www.hathitrust.org\/htrc HathiTrust Research Center. 2018. HathiTrust Research Center Homepage. (Feb. 2018). Retrieved Feb 13, 2018 from https:\/\/www.hathitrust.org\/htrc"},{"key":"e_1_3_2_1_7_1","volume-title":"Retrieved","author":"Stanford","year":"2018","unstructured":"Stanford CoreNLP. 2018 . Stanford CoreNLP Homepage. (Feb. 2018) . Retrieved Feb 13, 2018 from https:\/\/stanfordnlp.github.io\/CoreNLP\/ Stanford CoreNLP. 2018. Stanford CoreNLP Homepage. (Feb. 2018). Retrieved Feb 13, 2018 from https:\/\/stanfordnlp.github.io\/CoreNLP\/"},{"key":"e_1_3_2_1_8_1","volume-title":"Retrieved","author":"Database SQL","year":"2018","unstructured":"Postgre SQL Database . 2018 . PostgreSQL Homepage. (Feb. 2018) . Retrieved Feb 13, 2018 from https:\/\/www.postgresql.org\/ PostgreSQL Database. 2018. PostgreSQL Homepage. (Feb. 2018). Retrieved Feb 13, 2018 from https:\/\/www.postgresql.org\/"},{"key":"e_1_3_2_1_9_1","volume-title":"Retrieved","author":"Desktop Karst","year":"2018","unstructured":"Karst Desktop . 2018 . Karst Deskto Homepage. (Feb. 2018) . Retrieved Feb 13, 2018 from https:\/\/kb.iu.edu\/d\/bfwp Karst Desktop. 2018. Karst Deskto Homepage. (Feb. 2018). Retrieved Feb 13, 2018 from https:\/\/kb.iu.edu\/d\/bfwp"},{"volume-title":"Retrieved","year":"2018","key":"e_1_3_2_1_10_1","unstructured":"Elsevier. 2018 . ScienceDirect Repository. (Feb. 2018) . Retrieved Feb 13, 2018 from https:\/\/www.sciencedirect.com\/ Elsevier. 2018. ScienceDirect Repository. (Feb. 2018). Retrieved Feb 13, 2018 from https:\/\/www.sciencedirect.com\/"},{"key":"e_1_3_2_1_11_1","doi-asserted-by":"publisher","DOI":"10.5555\/3001460.3001507"},{"key":"e_1_3_2_1_12_1","volume-title":"Retrieved","author":"Feinerer Ingo","year":"2018","unstructured":"Ingo Feinerer . 2018 . Text Mining Package in R. (Feb. 2018) . Retrieved Feb 13, 2018 from http:\/\/tm.r-forge.r-project.org\/ Ingo Feinerer. 2018. Text Mining Package in R. (Feb. 2018). Retrieved Feb 13, 2018 from http:\/\/tm.r-forge.r-project.org\/"},{"key":"e_1_3_2_1_13_1","volume-title":"Retrieved","author":"Filesystem Lustre","year":"2018","unstructured":"Lustre Filesystem . 2018 . Lustre Homepage. (Feb. 2018) . Retrieved Feb 13, 2018 from http:\/\/lustre.org\/ Lustre Filesystem. 2018. Lustre Homepage. (Feb. 2018). Retrieved Feb 13, 2018 from http:\/\/lustre.org\/"},{"key":"e_1_3_2_1_14_1","volume-title":"Proceedings of the 6th International Conference on Pervasive Computing and Applications (ICPCA'11)","author":"Han Jing","year":"2011","unstructured":"Jing Han , Haihong E, Guan Le , and Jian Du . 2011 . Survey on NoSQL Database . In Proceedings of the 6th International Conference on Pervasive Computing and Applications (ICPCA'11) . IEEE. Jing Han, Haihong E, Guan Le, and Jian Du. 2011. Survey on NoSQL Database. In Proceedings of the 6th International Conference on Pervasive Computing and Applications (ICPCA'11). IEEE."},{"key":"e_1_3_2_1_15_1","doi-asserted-by":"publisher","DOI":"10.1145\/3130348.3130370"},{"key":"e_1_3_2_1_16_1","volume-title":"Retrieved","author":"Indiana University Network Science Institute.","year":"2018","unstructured":"Indiana University Network Science Institute. 2018 . IUNI Web Science of Science Homepage. (Feb. 2018) . Retrieved Feb 13, 2018 from https:\/\/iuni.iu.edu\/resources\/web-of-science Indiana University Network Science Institute. 2018. IUNI Web Science of Science Homepage. (Feb. 2018). Retrieved Feb 13, 2018 from https:\/\/iuni.iu.edu\/resources\/web-of-science"},{"key":"e_1_3_2_1_17_1","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2002.1017616"},{"key":"e_1_3_2_1_18_1","volume-title":"Retrieved","author":"Digital Library HathiTrust","year":"2018","unstructured":"HathiTrust Digital Library . 2018 . HathiTrust Digital Library Homepage. (Feb. 2018) . Retrieved Feb 13, 2018 from https:\/\/www.hathitrust.org\/ HathiTrust Digital Library. 2018. HathiTrust Digital Library Homepage. (Feb. 2018). Retrieved Feb 13, 2018 from https:\/\/www.hathitrust.org\/"},{"volume-title":"Retrieved","year":"2018","key":"e_1_3_2_1_19_1","unstructured":"Matlab. 2018 . Matlab Homepage. (Feb. 2018) . Retrieved Feb 13, 2018 from https:\/\/www.mathworks.com\/products\/matlab.html Matlab. 2018. Matlab Homepage. (Feb. 2018). Retrieved Feb 13, 2018 from https:\/\/www.mathworks.com\/products\/matlab.html"},{"volume-title":"Retrieved","year":"2018","key":"e_1_3_2_1_20_1","unstructured":"Matplotlib. 2018 . Matplotlib Homepage. (Feb. 2018) . Retrieved Feb 13, 2018 from https:\/\/matplotlib.org\/ Matplotlib. 2018. Matplotlib Homepage. (Feb. 2018). Retrieved Feb 13, 2018 from https:\/\/matplotlib.org\/"},{"key":"e_1_3_2_1_21_1","volume-title":"Retrieved","author":"Apache","year":"2018","unstructured":"Apache OpenNLP. 2018 . Apache OpenNLP Homepage. (Feb. 2018) . Retrieved Feb 13, 2018 from https:\/\/opennlp.apache.org\/ Apache OpenNLP. 2018. Apache OpenNLP Homepage. (Feb. 2018). Retrieved Feb 13, 2018 from https:\/\/opennlp.apache.org\/"},{"key":"e_1_3_2_1_22_1","volume-title":"Austerweil","author":"Priva Uriel Cohen","year":"2015","unstructured":"Uriel Cohen Priva and Joseph L . Austerweil . 2015 . Analyzing the History of Cognition using Topic Models. Cognition 135 (Feb. 2015), 4--9. Uriel Cohen Priva and Joseph L. Austerweil. 2015. Analyzing the History of Cognition using Topic Models. Cognition 135 (Feb. 2015), 4--9."},{"key":"e_1_3_2_1_23_1","volume-title":"Retrieved","author":"Project Jupyter","year":"2018","unstructured":"Jupyter Project . 2018 . Jupyter Project Homepage. (Feb. 2018) . Retrieved Feb 13, 2018 from http:\/\/jupyter.org\/ Jupyter Project. 2018. Jupyter Project Homepage. (Feb. 2018). Retrieved Feb 13, 2018 from http:\/\/jupyter.org\/"},{"key":"e_1_3_2_1_24_1","volume-title":"Retrieved","author":"\u0158ehu\u0159ek Radim","year":"2018","unstructured":"Radim \u0158ehu\u0159ek . 2018 . Gensim Homepage. (Feb. 2018) . Retrieved Feb 13, 2018 from https:\/\/radimrehurek.com\/gensim\/ Radim \u0158ehu\u0159ek. 2018. Gensim Homepage. (Feb. 2018). Retrieved Feb 13, 2018 from https:\/\/radimrehurek.com\/gensim\/"},{"key":"e_1_3_2_1_25_1","doi-asserted-by":"publisher","DOI":"10.1109\/4236.656066"},{"volume-title":"Retrieved","year":"2018","key":"e_1_3_2_1_26_1","unstructured":"RStudio. 2018 . RStudio Homepage. (Feb. 2018) . Retrieved Feb 13, 2018 from https:\/\/www.rstudio.com\/ RStudio. 2018. RStudio Homepage. (Feb. 2018). Retrieved Feb 13, 2018 from https:\/\/www.rstudio.com\/"},{"key":"e_1_3_2_1_27_1","doi-asserted-by":"crossref","unstructured":"Guangchen Ruan and Hui Zhang. 2016. In Conquering Big Data with High Performance Computing R. Arora (Ed.). Springer Chapter Large-scale Multimodal Data Exploration with Human in the Loop 253--268.  Guangchen Ruan and Hui Zhang. 2016. In Conquering Big Data with High Performance Computing R. Arora (Ed.). Springer Chapter Large-scale Multimodal Data Exploration with Human in the Loop 253--268.","DOI":"10.1007\/978-3-319-33742-5_12"},{"key":"e_1_3_2_1_28_1","volume-title":"Closed-loop Big Data Analysis with Visualization and Scalable Computing. Big Data Research 8 (Jan","author":"Ruan Guangchen","year":"2017","unstructured":"Guangchen Ruan and Hui Zhang . 2017. Closed-loop Big Data Analysis with Visualization and Scalable Computing. Big Data Research 8 (Jan . 2017 ), 12--26. Guangchen Ruan and Hui Zhang. 2017. Closed-loop Big Data Analysis with Visualization and Scalable Computing. Big Data Research 8 (Jan. 2017), 12--26."},{"key":"e_1_3_2_1_29_1","volume-title":"Retrieved","author":"Sinclair St\u00e9fan","year":"2018","unstructured":"St\u00e9fan Sinclair and Geoffrey Rockwell . 2018 . Getting Started with Spyral Notebooks. (Feb. 2018) . Retrieved March 22, 2018 from https:\/\/voyant-tools.org\/spyral\/alta-start St\u00e9fan Sinclair and Geoffrey Rockwell. 2018. Getting Started with Spyral Notebooks. (Feb. 2018). Retrieved March 22, 2018 from https:\/\/voyant-tools.org\/spyral\/alta-start"},{"key":"e_1_3_2_1_30_1","volume-title":"Retrieved","author":"Sinclair Stefan","year":"2018","unstructured":"Stefan Sinclair and Geoffrey Rockwell . 2018 . Voyant Tools Portal. (Feb. 2018) . Retrieved Feb 13, 2018 from https:\/\/voyant-tools.org\/ Stefan Sinclair and Geoffrey Rockwell. 2018. Voyant Tools Portal. (Feb. 2018). Retrieved Feb 13, 2018 from https:\/\/voyant-tools.org\/"},{"key":"e_1_3_2_1_31_1","volume-title":"Retrieved","author":"Spark Apache","year":"2018","unstructured":"Apache Spark . 2018 . Apache Spark Homepage. (Feb. 2018) . Retrieved Feb 13, 2018 from https:\/\/spark.apache.org\/ Apache Spark. 2018. Apache Spark Homepage. (Feb. 2018). Retrieved Feb 13, 2018 from https:\/\/spark.apache.org\/"},{"key":"e_1_3_2_1_32_1","volume-title":"Retrieved","author":"Toolkit Natural Language","year":"2018","unstructured":"Natural Language Toolkit . 2018 . Natural Language Toolkit Homepage. (Feb. 2018) . Retrieved Feb 13, 2018 from http:\/\/www.nltk.org\/ Natural Language Toolkit. 2018. Natural Language Toolkit Homepage. (Feb. 2018). Retrieved Feb 13, 2018 from http:\/\/www.nltk.org\/"},{"key":"e_1_3_2_1_33_1","volume-title":"Retrieved","author":"Vonnegut Kurt","year":"2018","unstructured":"Kurt Vonnegut . 2018 . Cat's Cradle Wiki Page. (Feb. 2018) . Retrieved Feb 13, 2018 from https:\/\/en.wikipedia.org\/wiki\/Cat%27s_Cradle Kurt Vonnegut. 2018. Cat's Cradle Wiki Page. (Feb. 2018). Retrieved Feb 13, 2018 from https:\/\/en.wikipedia.org\/wiki\/Cat%27s_Cradle"},{"key":"e_1_3_2_1_34_1","volume-title":"Proceedings of the 9th USENIX conference on Networked Systems Design and Implementation (NSDI'12)","author":"Zaharia Matei","year":"2012","unstructured":"Matei Zaharia , Mosharaf Chowdhury , Tathagata Das , Ankur Dave , Justin Ma , Murphy McCauley , Michael J. Franklin , Scott Shenker , and Ion Stoica . 2012 . Resilient Distributed Datasets: A Fault-tolerant Abstraction for in-memory Cluster Computing . In Proceedings of the 9th USENIX conference on Networked Systems Design and Implementation (NSDI'12) . USENIX Association, Berkley, CA. Matei Zaharia, Mosharaf Chowdhury, Tathagata Das, Ankur Dave, Justin Ma, Murphy McCauley, Michael J. Franklin, Scott Shenker, and Ion Stoica. 2012. Resilient Distributed Datasets: A Fault-tolerant Abstraction for in-memory Cluster Computing. In Proceedings of the 9th USENIX conference on Networked Systems Design and Implementation (NSDI'12). USENIX Association, Berkley, CA."},{"key":"e_1_3_2_1_35_1","volume-title":"Spark: Cluster Computing with Working Sets. In HotCloud (10)","author":"Zaharia Matei","year":"2010","unstructured":"Matei Zaharia , Mosharaf Chowdhury , Michael J. Franklin , Scott Shenker , and Ion Stoica . 2010 . Spark: Cluster Computing with Working Sets. In HotCloud (10) . USENIX Association , Berkley, CA . Matei Zaharia, Mosharaf Chowdhury, Michael J. Franklin, Scott Shenker, and Ion Stoica. 2010. Spark: Cluster Computing with Working Sets. In HotCloud (10). USENIX Association, Berkley, CA."},{"key":"e_1_3_2_1_36_1","doi-asserted-by":"publisher","DOI":"10.1145\/2608029.2608031"}],"event":{"name":"PEARC '18: Practice and Experience in Advanced Research Computing","acronym":"PEARC '18","location":"Pittsburgh PA USA"},"container-title":["Proceedings of the Practice and Experience on Advanced Research Computing"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3219104.3219153","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3219104.3219153","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,18]],"date-time":"2025-06-18T02:07:12Z","timestamp":1750212432000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3219104.3219153"}},"subtitle":["Balancing Accessibility with Scalability"],"short-title":[],"issued":{"date-parts":[[2018,7,22]]},"references-count":36,"alternative-id":["10.1145\/3219104.3219153","10.1145\/3219104"],"URL":"https:\/\/doi.org\/10.1145\/3219104.3219153","relation":{},"subject":[],"published":{"date-parts":[[2018,7,22]]},"assertion":[{"value":"2018-07-22","order":2,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}