{"created":"2023-10-03T00:48:56.278536+00:00","id":2000492,"links":{},"metadata":{"_buckets":{"deposit":"6ec419cb-5fce-423e-9047-a4cb0f944131"},"_deposit":{"created_by":188,"id":"2000492","owner":"15","owners":[188],"pid":{"revision_id":0,"type":"depid","value":"2000492"},"status":"published"},"_oai":{"id":"oai:kitami-it.repo.nii.ac.jp:02000492","sets":["2:6"]},"author_link":[],"item_7_biblio_info_6":{"attribute_name":"書誌情報","attribute_value_mlt":[{"bibliographicIssueDates":{"bibliographicIssueDate":"2023-09","bibliographicIssueDateType":"Issued"},"bibliographicPageStart":"1"}]},"item_7_date_granted_63":{"attribute_name":"学位授与年月日","attribute_value_mlt":[{"subitem_dategranted":"2023-09-05"}]},"item_7_degree_grantor_61":{"attribute_name":"学位授与機関","attribute_value_mlt":[{"subitem_degreegrantor":[{"subitem_degreegrantor_language":"ja","subitem_degreegrantor_name":"北見工業大学"}],"subitem_degreegrantor_identifier":[{"subitem_degreegrantor_identifier_name":"10106","subitem_degreegrantor_identifier_scheme":"kakenhi"}]}]},"item_7_degree_name_60":{"attribute_name":"学位名","attribute_value_mlt":[{"subitem_degreename":"博士（工学）","subitem_degreename_language":"ja"}]},"item_7_description_4":{"attribute_name":"抄録","attribute_value_mlt":[{"subitem_description":"In this study, I propose the use of online microblogs as review supplements and demonstrate their\napplicability through a designed tourist support system that aims to provide additional opinions\nand up-to-date points of interest to the less-known tourist spots. In realizing this proposal, I use\nInformation Extraction (IE), Artificial Intelligence (AI), and Natural Language Processing (NLP)\n- based techniques. The proposed approach folds into three.\nFirst, through the use of geotagged tweets. Tweets that contain geolocation information\nare considered geotagged and therefore treated as possible tourist on-spot opinions. The main\nchallenge, however, is to confirm the authenticity of the extracted tweets. This stage includes the\nuse of location clustering and classification techniques. Specifically, extracted geotagged tweets\nare clustered by using location information and then annotated taking into consideration specific\nfeatures applied to machine learning-based classification techniques. As for the machine learning\n(ML) algorithms, I adopt a fine-tuned transformer neural network-based BERT model which\nimplements the information of token context orientation for better classification.\nSecond, I studied geolocatability of ungeotagged tweets so that they can be used as review\nalternatives. Ungeotagged tweets have no geolocation information attached so it is difficult to\nassociate with specific location. Furthermore, Twitter data is typically noisy and consists of\nungrammatical or informal phraseology and non-standard vocabulary, which additionally causes\nthe feature sparsity problem, resulting in low classifier performance.\nTo address this, I proposed the use of a two-stage process, a transformer-based model for the\nclassification of primary tweets, and a combination of impact words like location mention or event\nmention for location inferring. Additionally, I evaluate a range of pre-processing techniques for text\ncategorization to accurately obtain a proper set that collectively contributes to the improvement\nof prediction accuracy. A classification framework created here relies on a fine-tuned transformer\nneural network model which learns from tweet contents and predicts the locations from which those\ntweets were sent - with a limited application in the detection of widely known general locations\n- such as tourist spots. I learned that the average 0.84 F1 score of a pre-trained DistilBERT\nlanguage model outperformed other tested models when tested on different pre-processing datasets.\nFurthermore, i evaluated the effect of impact words like location mention, and event mention on\nthe geolocation estimation, and model accuracy improvement when impact words are involved or\nremoved. To investigate the effect of impact words on a classification model, i first computed\nthe weighting of words using TFIDF and futher created a likelihood wordlist. I discovered model\naccuracy improvement as much as 6% when impact words are involved compared to when they\nare removed which suggests positive influence of impact words in geolocatability. I also discovered\nwrong weighted impact words that negatively contributes to the model performance and byeliminating them, the model F1 score improved by 3%.\nThird, I demonstrate the applicability of these two approaches by designing a tourist support\nsystem and mapping extracted opinions to their respective tourist spots as touristic information.","subitem_description_language":"en","subitem_description_type":"Abstract"}]},"item_7_dissertation_number_64":{"attribute_name":"学位授与番号","attribute_value_mlt":[{"subitem_dissertationnumber":"甲第211号"}]},"item_7_identifier_registration":{"attribute_name":"ID登録","attribute_value_mlt":[{"subitem_identifier_reg_text":"10.19000/0002000492","subitem_identifier_reg_type":"JaLC"}]},"item_7_select_15":{"attribute_name":"著者版フラグ","attribute_value_mlt":[{"subitem_select_item":["ETD"],"subitem_select_language":"en"}]},"item_7_text_66":{"attribute_name":"研究科・専攻名","attribute_value_mlt":[{"subitem_text_value":"生産基盤工学専攻"}]},"item_access_right":{"attribute_name":"アクセス権","attribute_value_mlt":[{"subitem_access_right":"open access","subitem_access_right_uri":"http://purl.org/coar/access_right/c_abf2"}]},"item_creator":{"attribute_name":"著者","attribute_type":"creator","attribute_value_mlt":[{"creatorNames":[{"creatorName":"Victor Alex Silaa","creatorNameLang":"en"}]}]},"item_files":{"attribute_name":"ファイル情報","attribute_type":"file","attribute_value_mlt":[{"accessrole":"open_access","date":[{"dateType":"Available","dateValue":"2023-10-03"}],"filename":"PhD_Thesis_SILAA _Sept4.pdf","filesize":[{"value":"5.8 MB"}],"format":"application/pdf","mimetype":"application/pdf","url":{"objectType":"fulltext","url":"https://kitami-it.repo.nii.ac.jp/record/2000492/files/PhD_Thesis_SILAA _Sept4.pdf"},"version_id":"d95dd601-fc0f-4520-9a7c-d4b3cfe24d7c"}]},"item_language":{"attribute_name":"言語","attribute_value_mlt":[{"subitem_language":"eng"}]},"item_resource_type":{"attribute_name":"資源タイプ","attribute_value_mlt":[{"resourcetype":"doctoral thesis","resourceuri":"http://purl.org/coar/resource_type/c_db06"}]},"item_title":"Web-based Safari Review System Development using Microblog Analyzed Data","item_titles":{"attribute_name":"タイトル","attribute_value_mlt":[{"subitem_title":"Web-based Safari Review System Development using Microblog Analyzed Data","subitem_title_language":"en"},{"subitem_title":"マイクロブログの解析データを利用したWebベースのサファリレビューシス テム開発","subitem_title_language":"ja"}]},"item_type_id":"7","owner":"188","path":["6"],"pubdate":{"attribute_name":"PubDate","attribute_value":"2023-10-03"},"publish_date":"2023-10-03","publish_status":"0","recid":"2000492","relation_version_is_last":true,"title":["Web-based Safari Review System Development using Microblog Analyzed Data"],"weko_creator_id":"188","weko_shared_id":-1},"updated":"2025-01-10T01:37:38.639008+00:00"}