<?xml version="1.0" encoding="UTF-8"?><xml><records><record><source-app name="Biblio" version="7.x">Drupal-Biblio</source-app><ref-type>10</ref-type><contributors><authors><author><style face="normal" font="default" size="100%">B. Devkota</style></author><author><style face="normal" font="default" size="100%">K. Kim</style></author><author><style face="normal" font="default" size="100%">C. Zhuang</style></author><author><style face="normal" font="default" size="100%">H. Miyazaki</style></author></authors></contributors><titles><title><style face="normal" font="default" size="100%">Disaggregate Hotel Evaluation by Using Diverse Aspects from User Reviews</style></title><secondary-title><style face="normal" font="default" size="100%">2019 IEEE International Conference on Big Data and Smart Computing (BigComp)</style></secondary-title></titles><keywords><keyword><style  face="normal" font="default" size="100%">Adaptation models</style></keyword><keyword><style  face="normal" font="default" size="100%">aspects</style></keyword><keyword><style  face="normal" font="default" size="100%">Coherence</style></keyword><keyword><style  face="normal" font="default" size="100%">coherent hotel aspects</style></keyword><keyword><style  face="normal" font="default" size="100%">customer satisfaction</style></keyword><keyword><style  face="normal" font="default" size="100%">data mining</style></keyword><keyword><style  face="normal" font="default" size="100%">Data models</style></keyword><keyword><style  face="normal" font="default" size="100%">disaggregate hotel evaluation</style></keyword><keyword><style  face="normal" font="default" size="100%">diverse aspects</style></keyword><keyword><style  face="normal" font="default" size="100%">Estimation</style></keyword><keyword><style  face="normal" font="default" size="100%">Feature extraction</style></keyword><keyword><style  face="normal" font="default" size="100%">fine-grained aspect level opinions</style></keyword><keyword><style  face="normal" font="default" size="100%">frequent noun-adjective co-occurrence statistics</style></keyword><keyword><style  face="normal" font="default" size="100%">hotel industry</style></keyword><keyword><style  face="normal" font="default" size="100%">hotel ranking</style></keyword><keyword><style  face="normal" font="default" size="100%">hotel reviews</style></keyword><keyword><style  face="normal" font="default" size="100%">latent aspects</style></keyword><keyword><style  face="normal" font="default" size="100%">Predictive models</style></keyword><keyword><style  face="normal" font="default" size="100%">purchase decision</style></keyword><keyword><style  face="normal" font="default" size="100%">statistical analysis</style></keyword><keyword><style  face="normal" font="default" size="100%">supervised methods</style></keyword><keyword><style  face="normal" font="default" size="100%">topic modeling</style></keyword><keyword><style  face="normal" font="default" size="100%">unsupervised learning</style></keyword><keyword><style  face="normal" font="default" size="100%">user attention</style></keyword><keyword><style  face="normal" font="default" size="100%">user reviews</style></keyword><keyword><style  face="normal" font="default" size="100%">word co-occurrence statistics</style></keyword><keyword><style  face="normal" font="default" size="100%">word embeddings</style></keyword></keywords><dates><year><style  face="normal" font="default" size="100%">2019</style></year><pub-dates><date><style  face="normal" font="default" size="100%">Feb</style></date></pub-dates></dates><language><style face="normal" font="default" size="100%">eng</style></language><abstract><style face="normal" font="default" size="100%">Experienced opinions about products and services can guide a potential user for a better purchase decision. Fine-grained aspect level opinions embedded within reviews must be explored to discover experienced users&#039; latent opinion about the aspects (i.e. features of products like cost, value for money, etc.) and their relative importance. In this paper, we present an unsupervised approach for discovering coherent hotel aspects based on the user attention. This model effectively integrates techniques like topic modeling and word embeddings along with the frequent noun-adjective co-occurrence statistics to automatically discover coherent hotel aspects. Further supervised methods are used to understand the user&#039;s relative emphasis on the aspects and finally rank the hotels. This method does not assume any predefined seed words and discovers coherent level aspects by directly using user attention and word co-occurrence statistics in addition to topic modeling and word embeddings. The performance evaluation of this method was done by collecting various hotel reviews from multiple travel websites. Results show that the proposed methods improved the baseline performance up to 90%. Hence, the results thus obtained are very promising and indicate that the system is simple, scalable and most of all accurate in ranking hotels based on the latent aspects expressed in the user reviews.</style></abstract></record><record><source-app name="Biblio" version="7.x">Drupal-Biblio</source-app><ref-type>10</ref-type><contributors><authors><author><style face="normal" font="default" size="100%">B. Devkota</style></author><author><style face="normal" font="default" size="100%">H. Miyazaki</style></author></authors></contributors><titles><title><style face="normal" font="default" size="100%">An Exploratory Study on the Generation and Distribution of Geotagged Tweets in Nepal</style></title><secondary-title><style face="normal" font="default" size="100%">2018 IEEE 3rd International Conference on Computing, Communication and Security (ICCCS)</style></secondary-title></titles><keywords><keyword><style  face="normal" font="default" size="100%">active user locations</style></keyword><keyword><style  face="normal" font="default" size="100%">clustering</style></keyword><keyword><style  face="normal" font="default" size="100%">Conferences</style></keyword><keyword><style  face="normal" font="default" size="100%">data mining</style></keyword><keyword><style  face="normal" font="default" size="100%">geotagged tweets</style></keyword><keyword><style  face="normal" font="default" size="100%">hotspots</style></keyword><keyword><style  face="normal" font="default" size="100%">human information behaviors</style></keyword><keyword><style  face="normal" font="default" size="100%">Kernel</style></keyword><keyword><style  face="normal" font="default" size="100%">live human sensors</style></keyword><keyword><style  face="normal" font="default" size="100%">Media</style></keyword><keyword><style  face="normal" font="default" size="100%">microblogging platform</style></keyword><keyword><style  face="normal" font="default" size="100%">Nepal</style></keyword><keyword><style  face="normal" font="default" size="100%">pattern clustering</style></keyword><keyword><style  face="normal" font="default" size="100%">Security</style></keyword><keyword><style  face="normal" font="default" size="100%">social media</style></keyword><keyword><style  face="normal" font="default" size="100%">social media platforms</style></keyword><keyword><style  face="normal" font="default" size="100%">social networking (online)</style></keyword><keyword><style  face="normal" font="default" size="100%">spatial clustering</style></keyword><keyword><style  face="normal" font="default" size="100%">spatial distribution</style></keyword><keyword><style  face="normal" font="default" size="100%">spatial patterns</style></keyword><keyword><style  face="normal" font="default" size="100%">spatial penetration</style></keyword><keyword><style  face="normal" font="default" size="100%">spatiotemporal patterns</style></keyword><keyword><style  face="normal" font="default" size="100%">spatiotemporal public opinion</style></keyword><keyword><style  face="normal" font="default" size="100%">time data</style></keyword><keyword><style  face="normal" font="default" size="100%">travel industry</style></keyword><keyword><style  face="normal" font="default" size="100%">tweet clusters</style></keyword><keyword><style  face="normal" font="default" size="100%">Twitter</style></keyword><keyword><style  face="normal" font="default" size="100%">twitter activities</style></keyword><keyword><style  face="normal" font="default" size="100%">twitter data</style></keyword><keyword><style  face="normal" font="default" size="100%">Urban areas</style></keyword><keyword><style  face="normal" font="default" size="100%">world wide web today</style></keyword></keywords><dates><year><style  face="normal" font="default" size="100%">2018</style></year><pub-dates><date><style  face="normal" font="default" size="100%">Oct</style></date></pub-dates></dates><language><style face="normal" font="default" size="100%">eng</style></language><abstract><style face="normal" font="default" size="100%">Social media platforms contribute a huge part of the content available on the world wide web today. These platforms act as a rich source of real time data from live human sensors. These media disseminate spatiotemporal public opinion regarding a range of events, activities and human information behaviors. This paper explores the active user locations and spatial penetration of popular microblogging platform, Twitter, in Nepal. A heatmap visualization is used to show the intensity and distribution of the spatial patterns of Twitter activities in different parts of Nepal. Clustering is a popular technique for knowledge discovery, so spatial clustering is applied to groups tweets spatially into different classes. Such spatial clustering helps in the identification of areas of similar twitter activities and shows the distribution of the spatial patterns in different parts of Nepal. Tweet clusters are observed mainly in the main cities and the tourism centers. Further, an examination of the twitter data shared by the local Nepalese people and the foreigners are shown. This study contributes the research line by providing insights to better understand the spatiotemporal patterns and hotspots of tweets in Nepal. Such patterns and hotspots have an immense practical value that can be attributable to a place in order to derive meaningful insights related to various domains like a disease, crime, tourism, etc.</style></abstract></record></records></xml>