Pub Date : 2022-11-03DOI: 10.1109/SMAP56125.2022.9941803
Maria Nefeli Nikiforos, Konstantina Deliveri, Katia Lida Kermanidis, Adamantia G. Pateli
Despite their educational level and professional qualifications, an important percentage of highly-skilled migrants and refugees find employment in low-skill vocations throughout the world. Typical vocational domains include agriculture, cooking, crafting, construction, and hospitality. As a first step towards developing an educational tool for helping such underprivileged communities become acquainted with the sublanguage of their vocational domain in their host country, automatic domain identification among the aforementioned domains was attempted in this paper, using domain-specific textual data. Wikis and social networks provide a valuable data source for data mining, Natural Language Processing and machine learning tasks. Wikipedia articles, in regard to these domains, were collected and processed in order to create a novel text data set. Extracted linguistic features were used in the experiments with Random Forest combined with Adaboost, and Gradient Boosted Trees. The machine learning models achieved high performance in vocational domain identification (up to 99.93% accuracy).
{"title":"Machine Learning on Wikipedia Text for the Automatic Identification of Vocational Domains of Significance for Displaced Communities","authors":"Maria Nefeli Nikiforos, Konstantina Deliveri, Katia Lida Kermanidis, Adamantia G. Pateli","doi":"10.1109/SMAP56125.2022.9941803","DOIUrl":"https://doi.org/10.1109/SMAP56125.2022.9941803","url":null,"abstract":"Despite their educational level and professional qualifications, an important percentage of highly-skilled migrants and refugees find employment in low-skill vocations throughout the world. Typical vocational domains include agriculture, cooking, crafting, construction, and hospitality. As a first step towards developing an educational tool for helping such underprivileged communities become acquainted with the sublanguage of their vocational domain in their host country, automatic domain identification among the aforementioned domains was attempted in this paper, using domain-specific textual data. Wikis and social networks provide a valuable data source for data mining, Natural Language Processing and machine learning tasks. Wikipedia articles, in regard to these domains, were collected and processed in order to create a novel text data set. Extracted linguistic features were used in the experiments with Random Forest combined with Adaboost, and Gradient Boosted Trees. The machine learning models achieved high performance in vocational domain identification (up to 99.93% accuracy).","PeriodicalId":432172,"journal":{"name":"2022 17th International Workshop on Semantic and Social Media Adaptation & Personalization (SMAP)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-11-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131100775","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2022-11-03DOI: 10.1109/SMAP56125.2022.9941866
Ioannis Papanikolaou, Katerina Tzafilkou
This research explores the user emotional states, searched keywords and intention to visit a promoted touristic place, after being exposed in different types of a social media tourism campaign, ‘Pure New Zealand’. Sixty-one users participated in the exploratory study, divided into 3 groups. The first group saw a video campaign, the second a set of images and the third both. Face tracking tools were used to monitor the user emotional levels of valence and arousal, while a post-task self-reported measure collected information about the user-generated keywords, their intention to visit New Zealand, and their perceived emotional states. Later we compared the results between the two selected research tools. The results indicated that: a) users scored higher emotional levels when using the self-reported tool than the real time data counterparts, b) user subjected to the combined ad treatment elicited significantly higher arousal levels than the other groups. Based on the keywords discovery results, this study also c) proposes a process of dividing keywords to easier discover associations between campaign-based keywords and user’s intent. For the last part, we can argue that the 100% Pure New Zealand initiative matched 37% of keywords reported by our participants
本研究在不同类型的社交媒体旅游活动“纯净新西兰”中曝光后，探讨了用户的情绪状态、搜索关键词和访问被推广的旅游地点的意愿。61名用户参与了探索性研究，分为3组。第一组看了一段视频，第二组看了一组图片，第三组都看了。面部追踪工具被用来监测用户的情绪水平，而任务后自我报告的测量收集了用户生成的关键词、他们访问新西兰的意图和他们感知到的情绪状态的信息。后来我们比较了两种选择的研究工具的结果。结果表明:a)使用自我报告工具的用户比使用实时数据的用户获得更高的情绪水平;b)联合处理的用户引起的唤醒水平显著高于其他组。基于关键词发现结果，本研究还c)提出了一个划分关键词的过程，以更容易地发现基于活动的关键词与用户意图之间的关联。对于最后一部分，我们可以说100% Pure New Zealand倡议匹配了参与者报告的37%的关键词
{"title":"Online Marketing Synergy Combining self-reported and real-time data to examine the effect of user-generated keywords and emotions for a tourism campaign","authors":"Ioannis Papanikolaou, Katerina Tzafilkou","doi":"10.1109/SMAP56125.2022.9941866","DOIUrl":"https://doi.org/10.1109/SMAP56125.2022.9941866","url":null,"abstract":"This research explores the user emotional states, searched keywords and intention to visit a promoted touristic place, after being exposed in different types of a social media tourism campaign, ‘Pure New Zealand’. Sixty-one users participated in the exploratory study, divided into 3 groups. The first group saw a video campaign, the second a set of images and the third both. Face tracking tools were used to monitor the user emotional levels of valence and arousal, while a post-task self-reported measure collected information about the user-generated keywords, their intention to visit New Zealand, and their perceived emotional states. Later we compared the results between the two selected research tools. The results indicated that: a) users scored higher emotional levels when using the self-reported tool than the real time data counterparts, b) user subjected to the combined ad treatment elicited significantly higher arousal levels than the other groups. Based on the keywords discovery results, this study also c) proposes a process of dividing keywords to easier discover associations between campaign-based keywords and user’s intent. For the last part, we can argue that the 100% Pure New Zealand initiative matched 37% of keywords reported by our participants","PeriodicalId":432172,"journal":{"name":"2022 17th International Workshop on Semantic and Social Media Adaptation & Personalization (SMAP)","volume":"39 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-11-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131758789","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2022-11-03DOI: 10.1109/SMAP56125.2022.9941858
A. Antoniou, Stella Sylaiou, Manolis Wallace, Konstantinos Evaggelidis, V. Poulopoulos
The ARTEST project aimed at improving teaching and learning in Digital Humanities. However, all planned project activities had to be altered due to COVID 19 and the first project training workshop had to shift to an online mode. This shift allowed project partners and workshop participants to reconsider the present and future of teaching and learning under the light of the pandemic and the possibility of having hybrid modes of learning in the future even after the end of the pandemic. The present work shows results from the 2-day workshop, as well as conclusions on the future of the field.
{"title":"The ARTEST project: the future of digital humanities teaching and learning","authors":"A. Antoniou, Stella Sylaiou, Manolis Wallace, Konstantinos Evaggelidis, V. Poulopoulos","doi":"10.1109/SMAP56125.2022.9941858","DOIUrl":"https://doi.org/10.1109/SMAP56125.2022.9941858","url":null,"abstract":"The ARTEST project aimed at improving teaching and learning in Digital Humanities. However, all planned project activities had to be altered due to COVID 19 and the first project training workshop had to shift to an online mode. This shift allowed project partners and workshop participants to reconsider the present and future of teaching and learning under the light of the pandemic and the possibility of having hybrid modes of learning in the future even after the end of the pandemic. The present work shows results from the 2-day workshop, as well as conclusions on the future of the field.","PeriodicalId":432172,"journal":{"name":"2022 17th International Workshop on Semantic and Social Media Adaptation & Personalization (SMAP)","volume":"41 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-11-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133740919","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
京公网安备 11010802042870号
京ICP备2023020795号-1
扫码关注我们
求助内容：
应助结果提醒方式：