MERAL Myanmar Education Research and Learning Portal
Item
{"_buckets": {"deposit": "8d67f194-84c7-462b-9faa-790cdb72f791"}, "_deposit": {"created_by": 45, "id": "5355", "owner": "45", "owners": [45], "owners_ext": {"displayname": "", "username": ""}, "pid": {"revision_id": 0, "type": "recid", "value": "5355"}, "status": "published"}, "_oai": {"id": "oai:meral.edu.mm:recid/5355", "sets": ["user-uit"]}, "communities": ["uit"], "item_1583103067471": {"attribute_name": "Title", "attribute_value_mlt": [{"subitem_1551255647225": "Semi-supervised Event Message Identification System for Targeted Domain", "subitem_1551255648112": "en"}]}, "item_1583103085720": {"attribute_name": "Description", "attribute_value_mlt": [{"interim": "Social media have become increasingly popular\ncomponents of our everyday lives in today’s globalizing society.\nThey provide a context where people across the world can\ncommunicate, exchange messages, share knowledge, and\ninteract with each other regardless of the distance that\nseparates them. This research trend, extraction of events for\nspecific domain from these social media is emerging speedily\nranging from business intelligence to nation security field. The\nshort length of Twitter messages and frequent use of informal\nand ungrammatical language challenge many long standing\napproaches for automatically detecting and categorizing events\nusing streamed data in Event Message Identification system. A\nsemi-supervised approach with Support Vector Machine (SVM)\nin combination with the corpus to identify the events from\ntwitter for targeted domain in specific location is proposed in\nthis paper. The experimental results show that the proposed\nsemi-supervised SVM model is more efficient than a strong\nstate-of-the-art semi-supervised classification model of Logic\nRegression, Naïve Bayes and Decision Tree."}]}, "item_1583103108160": {"attribute_name": "Keywords", "attribute_value_mlt": [{"interim": "Social media"}, {"interim": "Twitter"}, {"interim": "Semi-supervised"}, {"interim": "Events"}, {"interim": "SVM"}]}, "item_1583103120197": {"attribute_name": "Files", "attribute_type": "file", "attribute_value_mlt": [{"accessrole": "open_no", "date": [{"dateType": "Available", "dateValue": "2020-09-14"}], "displaytype": "preview", "filename": "Semi-supervised Event Message Identification System for Targeted Domain.pdf", "filesize": [{"value": "424 Kb"}], "format": "application/pdf", "licensefree": "©2018 IEEE", "licensetype": "license_free", "url": {"url": "https://meral.edu.mm/record/5355/files/Semi-supervised Event Message Identification System for Targeted Domain.pdf"}, "version_id": "177682fe-50ba-4f6a-8aa9-f8b726cc52e6"}]}, "item_1583103147082": {"attribute_name": "Conference papers", "attribute_value_mlt": [{"subitem_acronym": "IEEE, ICTT", "subitem_c_date": "8-11 October, 2018", "subitem_conference_title": "18th IEEE International Conference on Communication Technology", "subitem_place": "China"}]}, "item_1583105942107": {"attribute_name": "Authors", "attribute_value_mlt": [{"subitem_authors": [{"subitem_authors_fullname": "San San Nwe"}, {"subitem_authors_fullname": "Nang Saing Moon Kham"}]}]}, "item_1583108359239": {"attribute_name": "Upload type", "attribute_value_mlt": [{"interim": "Publication"}]}, "item_1583108428133": {"attribute_name": "Publication type", "attribute_value_mlt": [{"interim": "Conference paper"}]}, "item_1583159729339": {"attribute_name": "Publication date", "attribute_value": "2018-10-11"}, "item_title": "Semi-supervised Event Message Identification System for Targeted Domain", "item_type_id": "21", "owner": "45", "path": ["1596102391527"], "permalink_uri": "http://hdl.handle.net/20.500.12678/0000005355", "pubdate": {"attribute_name": "Deposited date", "attribute_value": "2020-09-14"}, "publish_date": "2020-09-14", "publish_status": "0", "recid": "5355", "relation": {}, "relation_version_is_last": true, "title": ["Semi-supervised Event Message Identification System for Targeted Domain"], "weko_shared_id": -1}
Semi-supervised Event Message Identification System for Targeted Domain
http://hdl.handle.net/20.500.12678/0000005355
http://hdl.handle.net/20.500.12678/00000053555e813c26-8191-4da2-87a4-6f1527128cfe
8d67f194-84c7-462b-9faa-790cdb72f791
Publication type | ||||||
---|---|---|---|---|---|---|
Conference paper | ||||||
Upload type | ||||||
Publication | ||||||
Title | ||||||
Title | Semi-supervised Event Message Identification System for Targeted Domain | |||||
Language | en | |||||
Publication date | 2018-10-11 | |||||
Authors | ||||||
San San Nwe | ||||||
Nang Saing Moon Kham | ||||||
Description | ||||||
Social media have become increasingly popular components of our everyday lives in today’s globalizing society. They provide a context where people across the world can communicate, exchange messages, share knowledge, and interact with each other regardless of the distance that separates them. This research trend, extraction of events for specific domain from these social media is emerging speedily ranging from business intelligence to nation security field. The short length of Twitter messages and frequent use of informal and ungrammatical language challenge many long standing approaches for automatically detecting and categorizing events using streamed data in Event Message Identification system. A semi-supervised approach with Support Vector Machine (SVM) in combination with the corpus to identify the events from twitter for targeted domain in specific location is proposed in this paper. The experimental results show that the proposed semi-supervised SVM model is more efficient than a strong state-of-the-art semi-supervised classification model of Logic Regression, Naïve Bayes and Decision Tree. |
||||||
Keywords | ||||||
Social media, Twitter, Semi-supervised, Events, SVM | ||||||
Conference papers | ||||||
IEEE, ICTT | ||||||
8-11 October, 2018 | ||||||
18th IEEE International Conference on Communication Technology | ||||||
China |