{"corpus_id":32411082,"paper_sha":"9b1369d6b6db514608c56084ceb4be3c9fb143de","doi":"10.1007/s10796-017-9741-7","arxiv_id":null,"pmid":null,"pmcid":null,"mag_id":2593681087,"dblp_id":"journals/isf/ChoiL17","acl_id":null,"title":"Data properties and the performance of sentiment classification for electronic commerce applications","year":2017,"publication_date":"2017-03-09","venue":"Inf. Syst. Frontiers","journal":{"name":"Information Systems Frontiers","pages":"993-1012","volume":"19"},"journal_issn":null,"journal_title":null,"publication_types":["JournalArticle","Review"],"pubmed_pub_types":null,"s2_fields_of_study":["Business","Computer Science"],"reference_count":98,"citation_count":55,"influential_citation_count":0,"is_open_access":true,"arxiv_categories":null,"arxiv_license":null,"arxiv_journal_ref":null,"mesh_headings":null,"chemicals":null,"comments_corrections":null,"source_flags":1,"s2_open_access_pdf_url":"https://link.springer.com/content/pdf/10.1007%2Fs10796-017-9741-7.pdf","s2_open_access_landing_url":"https://www.semanticscholar.org/paper/9b1369d6b6db514608c56084ceb4be3c9fb143de","s2_open_access_license":"CCBY","s2_open_access_status":"HYBRID","pmc_open_access_pdf_url":null,"pmc_open_access_landing_url":null,"pmc_open_access_license":null,"pmc_open_access_status":null,"unpaywall_open_access_pdf_url":null,"unpaywall_open_access_landing_url":null,"unpaywall_open_access_license":null,"unpaywall_open_access_status":null,"abstract":"Sentiment classification has played an important role in various research area including e-commerce applications and a number of advanced Computational Intelligence techniques including machine learning and computational linguistics have been proposed in the literature for improved sentiment classification results. While such studies focus on improving performance with new techniques or extending existing algorithms based on previously used dataset, few studies provide practitioners with insight on what techniques are better for their datasets that have different properties. This paper applies four different sentiment classification techniques from machine learning (Naïve Bayes, SVM and Decision Tree) and sentiment orientation approaches to datasets obtained from various sources (IMDB, Twitter, Hotel review, and Amazon review datasets) to learn how different data properties including dataset size, length of target documents, and subjectivity of data affect the performance of those techniques. The results of computational experiments confirm the sensitivity of the techniques on data properties including training data size, the document length and subjectivity of training /test data in the improvement of performances of techniques. The theoretical and practical implications of the findings are discussed.","claims":[{"public_id":"cl_a1cff5370d20bcfc765a764397f1249e","status":"active","text":"Experiments on IMDB, Twitter, hotel review, and Amazon review datasets were used to examine how data properties affect sentiment classification performance.","confidence":0.94,"contributors":[{"id":1,"public_id":"12632b8b5f","public_label":"Anonymous (12632b8b5f)","roles":["extraction"],"url":"https://sah.borca.ai/u/12632b8b5f"}],"url":"https://sah.borca.ai/claims/cl_a1cff5370d20bcfc765a764397f1249e"},{"public_id":"cl_3e7c97ecab7e0350c7c31409d69251ff","status":"active","text":"Naïve Bayes, SVM, decision tree, and sentiment orientation approaches were compared across datasets with different properties.","confidence":0.92,"contributors":[{"id":1,"public_id":"12632b8b5f","public_label":"Anonymous (12632b8b5f)","roles":["extraction"],"url":"https://sah.borca.ai/u/12632b8b5f"}],"url":"https://sah.borca.ai/claims/cl_3e7c97ecab7e0350c7c31409d69251ff"},{"public_id":"cl_5613418d160a2cfb9a2d595f9ba0d710","status":"active","text":"Sentiment classification techniques are sensitive to dataset size, document length, and the subjectivity of training and test data.","confidence":0.96,"contributors":[{"id":1,"public_id":"12632b8b5f","public_label":"Anonymous (12632b8b5f)","roles":["extraction"],"url":"https://sah.borca.ai/u/12632b8b5f"}],"url":"https://sah.borca.ai/claims/cl_5613418d160a2cfb9a2d595f9ba0d710"}],"concepts":[{"public_id":"co_0a6b4dedaba0962e273b94fc05b85e94","status":"active","name":"subjectivity of training/test data","description":"The degree to which the training and evaluation texts express subjective opinions rather than objective statements.","types":["dataset property"],"aliases":["subjectivity of data"],"contributors":[{"id":1,"public_id":"12632b8b5f","public_label":"Anonymous (12632b8b5f)","roles":["extraction"],"url":"https://sah.borca.ai/u/12632b8b5f"}],"url":"https://sah.borca.ai/concepts/co_0a6b4dedaba0962e273b94fc05b85e94"},{"public_id":"co_199d96545c6d1406a75f443e1a9cceac","status":"active","name":"Naïve Bayes","description":"A probabilistic machine learning classifier used for text classification.","types":["machine learning method"],"aliases":["Naive Bayes"],"contributors":[{"id":1,"public_id":"12632b8b5f","public_label":"Anonymous (12632b8b5f)","roles":["extraction"],"url":"https://sah.borca.ai/u/12632b8b5f"}],"url":"https://sah.borca.ai/concepts/co_199d96545c6d1406a75f443e1a9cceac"},{"public_id":"co_214c7bd534541c3054705e634a92ee7c","status":"active","name":"hotel review dataset","description":"A dataset of hotel reviews used for sentiment classification experiments.","types":["dataset"],"aliases":["Hotel review"],"contributors":[{"id":1,"public_id":"12632b8b5f","public_label":"Anonymous (12632b8b5f)","roles":["extraction"],"url":"https://sah.borca.ai/u/12632b8b5f"}],"url":"https://sah.borca.ai/concepts/co_214c7bd534541c3054705e634a92ee7c"},{"public_id":"co_2cd148fe7e247152b84e79ce3db969e7","status":"active","name":"sentiment classification","description":"A text classification task that assigns sentiment labels such as positive or negative.","types":["task"],"aliases":["sentiment analysis classification"],"contributors":[{"id":1,"public_id":"12632b8b5f","public_label":"Anonymous (12632b8b5f)","roles":["extraction"],"url":"https://sah.borca.ai/u/12632b8b5f"}],"url":"https://sah.borca.ai/concepts/co_2cd148fe7e247152b84e79ce3db969e7"},{"public_id":"co_55706122c971dd1a4321dbb72358d81a","status":"active","name":"decision tree","description":"A tree-structured machine learning classifier used for supervised classification.","types":["machine learning method"],"aliases":[],"contributors":[{"id":1,"public_id":"12632b8b5f","public_label":"Anonymous (12632b8b5f)","roles":["extraction"],"url":"https://sah.borca.ai/u/12632b8b5f"}],"url":"https://sah.borca.ai/concepts/co_55706122c971dd1a4321dbb72358d81a"},{"public_id":"co_62127a187d6dc8ea49055687381e6590","status":"active","name":"IMDB","description":"A movie review dataset used as one of the sentiment classification sources.","types":["dataset"],"aliases":[],"contributors":[{"id":1,"public_id":"12632b8b5f","public_label":"Anonymous (12632b8b5f)","roles":["extraction"],"url":"https://sah.borca.ai/u/12632b8b5f"}],"url":"https://sah.borca.ai/concepts/co_62127a187d6dc8ea49055687381e6590"},{"public_id":"co_6eb0b485dec6d2724e02a1fd138ada88","status":"active","name":"Amazon review dataset","description":"A dataset of product reviews from Amazon used for sentiment classification experiments.","types":["dataset"],"aliases":["Amazon review"],"contributors":[{"id":1,"public_id":"12632b8b5f","public_label":"Anonymous (12632b8b5f)","roles":["extraction"],"url":"https://sah.borca.ai/u/12632b8b5f"}],"url":"https://sah.borca.ai/concepts/co_6eb0b485dec6d2724e02a1fd138ada88"},{"public_id":"co_7fde93cd7cbd63be884f6b5518191ab2","status":"active","name":"dataset size","description":"The number of labeled or available instances in a dataset.","types":["dataset property"],"aliases":["training data size"],"contributors":[{"id":1,"public_id":"12632b8b5f","public_label":"Anonymous (12632b8b5f)","roles":["extraction"],"url":"https://sah.borca.ai/u/12632b8b5f"}],"url":"https://sah.borca.ai/concepts/co_7fde93cd7cbd63be884f6b5518191ab2"},{"public_id":"co_904a3b844cc94c4b81bb82133a562e5e","status":"active","name":"document length","description":"The length of the text documents being classified.","types":["dataset property"],"aliases":["length of target documents"],"contributors":[{"id":1,"public_id":"12632b8b5f","public_label":"Anonymous (12632b8b5f)","roles":["extraction"],"url":"https://sah.borca.ai/u/12632b8b5f"}],"url":"https://sah.borca.ai/concepts/co_904a3b844cc94c4b81bb82133a562e5e"},{"public_id":"co_967c3cb454e2edaea3333f1d1ca416e9","status":"active","name":"Twitter","description":"A collection of social media texts used as one of the sentiment classification datasets.","types":["dataset"],"aliases":[],"contributors":[{"id":1,"public_id":"12632b8b5f","public_label":"Anonymous (12632b8b5f)","roles":["extraction"],"url":"https://sah.borca.ai/u/12632b8b5f"}],"url":"https://sah.borca.ai/concepts/co_967c3cb454e2edaea3333f1d1ca416e9"},{"public_id":"co_9d991fa230009ba48ba36a7f247b6051","status":"active","name":"sentiment orientation approaches","description":"Methods that infer sentiment polarity from oriented words or sentiment-bearing expressions.","types":["method"],"aliases":["sentiment orientation"],"contributors":[{"id":1,"public_id":"12632b8b5f","public_label":"Anonymous (12632b8b5f)","roles":["extraction"],"url":"https://sah.borca.ai/u/12632b8b5f"}],"url":"https://sah.borca.ai/concepts/co_9d991fa230009ba48ba36a7f247b6051"},{"public_id":"co_b12304a685218146407c089ae261a3a6","status":"active","name":"SVM","description":"A support vector machine classifier used for sentiment classification.","types":["machine learning method"],"aliases":["support vector machine"],"contributors":[{"id":1,"public_id":"12632b8b5f","public_label":"Anonymous (12632b8b5f)","roles":["extraction"],"url":"https://sah.borca.ai/u/12632b8b5f"}],"url":"https://sah.borca.ai/concepts/co_b12304a685218146407c089ae261a3a6"}],"external_ids":{"DOI":"10.1007/s10796-017-9741-7","ArXiv":null,"PubMed":null,"PubMedCentral":null,"MAG":2593681087,"DBLP":"journals/isf/ChoiL17","ACL":null},"open_access":{"is_open_access":true,"pdf_url":"https://link.springer.com/content/pdf/10.1007%2Fs10796-017-9741-7.pdf","landing_url":"https://www.semanticscholar.org/paper/9b1369d6b6db514608c56084ceb4be3c9fb143de","source":"semantic_scholar","pdf_url_source":"semantic_scholar_open_access_pdf","license":"CCBY","status":"HYBRID","reason":null},"reference_availability":{"status":"available","references_indexed":true,"full_text_available":false,"full_text_source":null,"count_basis":"semantic_scholar_metadata","extraction_status":"not_applicable","reason":null},"source":{"provider":"episteme2","base_corpus":"semantic_scholar_dump","freshness_mode":"unknown","basis":["semantic_scholar_metadata","postgres_metadata"],"limits":["paper metadata is based on indexed upstream scholarly datasets","claims and concepts are available only for extracted papers","absence of claims or concepts means no extracted graph data is available in this response"],"status":"available","degraded":false,"degraded_reasons":[],"diagnostics":{"status":"available","degraded":false,"degraded_reasons":[],"metadata_status":"available","graph_status":"available","abstract_status":"available"},"source_flags":1},"paper_id":635086,"paper_uid":"33def13e-d819-4db7-90a8-f8d7e05c0971","canonical_identity":{"paper_id":635086,"paper_uid":"33def13e-d819-4db7-90a8-f8d7e05c0971","identity_status":"available","lookup_basis":"semantic_scholar_external_id","compatibility_path":"corpus_id"},"url":"https://sah.borca.ai/papers/32411082"}