FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W3008122813> ?p ?o ?g. }

• W3008122813 abstract "In recent years, social media platforms, such as Twitter and Webio, have become popular sources of information on the web. These platforms contain a wealth of valuable information about user opinions, user interests, events and more. People typically use these platforms to discuss different topics, share their opinions about them and engage in question-andanswer sessions. For example, regarding smartphones, users might discuss the main aspects of a smartphone, such as the overall design, battery capacity, screen size and camera. The natural hierarchical structure of those concepts is often hidden in social media. Discovering the hidden structure can helps users understand people’ preference to a certain topic at different levels of granularity, and show the reasons why they prefer this topic. Over the past decade, research on hierarchical topic models has shown considerable progress. However, these studies may not always be directly applicable to social media due to the shortness and the shallow meaning of social media messages.There are three major challenges when dealing with social media texts. Firstly, compared with traditionally long texts, social media texts suffer from sparsity, and this issuemay result in an incomprehensible and incorrect concept hierarchy. Secondly, social media contains useful information such as social opinions and information about users. Most existing methods perform a flat sentiment analysis on each extracted aspects independently, and ignore the concept hierarchy. In fact, we need to make the sentiment analysis finegrained in order to simultaneously extract the aspects and summarise people’ opinions on those discovered aspects. Thirdly, the current models only discover the concept hierarchy ignoring the community structure of users. Maintaining the consistency of user’s interest on several communities according to various topics and sentiment information is a challenging problem.In this thesis, the limitations of the existing work are addressed and effective solutions are proposed. First, in order to discover the hierarchical structure of social media content, a novel approach called the context coherence model (CCM) is proposed. It recursively top down: (1) organizes the concepts discussed by users in social media texts; and (2) identifies the hierarchical relations among concepts. In the CCM, a new measurement called context coherence is introduced that analyses words in social media texts and determines the similarities among them. Then, the hierarchical relationship between words is determined by recursively partitioning the whole corpus into smaller parts according to the similarity results. Finally, a merging operation is performed to find similar words, group them under the same topic and remove duplicated topics. The approach is evaluated on two real-world data sets. The experiments show that the proposed approach can effectively reveal the hidden structure in social media.Opinions are now reflected in social media on a wide range of topics: trends in pop music, fashion, politics, financial markets, natural disaster responses, sales of products and services, etc. For example, companies may want to understand the feelings of consumers towards their products or services at different levels of granularity. Therefore, the problem of hierarchical extraction is extended to consider sentiment analysis. A structured sentiment analysis (SSA) approach is proposed that summarizes users’ feelings towards those concepts discovered in the tree. Given users’ messages, the hierarchical clustering method is proposed to detect the top aspects interest users, based on their messages, and attach users’ attitudes to them. To perform sentiment analysis, a top-down, lexicon-based approach was designed to identify the polarity of top aspects of a topic. Finally, a simple summarization method was developed to answer questions such as: (1) What is the overall popularity of the product or service? (2) Why do people like or dislike the product or service? and (3) What are the most favourable and unfavourable aspects?Third, modelling the interests of users is particularly important and can help organizations to understand and analyse users’ behaviours and locate influential users at different granularity levels using their sentiment information. A probabilistic model, namely,the hierarchical user sentiment/topic model (HUSTM), is proposed to discover the hidden structure of topics and users while performing sentiment analysis in a unified way. In HUSTM, users who share the same topic and opinion are grouped within the same community. In this approach, the entire structure is a tree where each node is decomposed into a topic/sentiment node and a user-sentiment node. The topic/sentiment node is, in turn, a mixed distribution of words, while the user-sentiment node is a mixed distribution of users. To experimentally demonstrate the advantages of the approach, three real-world data sets were used. The results showed that, compared to other state-of-the-art techniques, the HUSTM approach can more successfully capture users’ interests." @default.
• W3008122813 created "2020-03-06" @default.
• W3008122813 creator A5078056378 @default.
• W3008122813 date "2020-01-30" @default.
• W3008122813 modified "2023-09-27" @default.
• W3008122813 title "Structured sentiment analysis in social media" @default.
• W3008122813 doi "https://doi.org/10.14264/uql.2020.36" @default.
• W3008122813 hasPublicationYear "2020" @default.
• W3008122813 type Work @default.
• W3008122813 sameAs 3008122813 @default.
• W3008122813 citedByCount "0" @default.
• W3008122813 crossrefType "dissertation" @default.
• W3008122813 hasAuthorship W3008122813A5078056378 @default.
• W3008122813 hasBestOaLocation W30081228132 @default.
• W3008122813 hasConcept C136764020 @default.
• W3008122813 hasConcept C154945302 @default.
• W3008122813 hasConcept C15744967 @default.
• W3008122813 hasConcept C17744445 @default.
• W3008122813 hasConcept C199539241 @default.
• W3008122813 hasConcept C23123220 @default.
• W3008122813 hasConcept C2522767166 @default.
• W3008122813 hasConcept C2780876879 @default.
• W3008122813 hasConcept C31170391 @default.
• W3008122813 hasConcept C41008148 @default.
• W3008122813 hasConcept C518677369 @default.
• W3008122813 hasConcept C542102704 @default.
• W3008122813 hasConcept C66402592 @default.
• W3008122813 hasConceptScore W3008122813C136764020 @default.
• W3008122813 hasConceptScore W3008122813C154945302 @default.
• W3008122813 hasConceptScore W3008122813C15744967 @default.
• W3008122813 hasConceptScore W3008122813C17744445 @default.
• W3008122813 hasConceptScore W3008122813C199539241 @default.
• W3008122813 hasConceptScore W3008122813C23123220 @default.
• W3008122813 hasConceptScore W3008122813C2522767166 @default.
• W3008122813 hasConceptScore W3008122813C2780876879 @default.
• W3008122813 hasConceptScore W3008122813C31170391 @default.
• W3008122813 hasConceptScore W3008122813C41008148 @default.
• W3008122813 hasConceptScore W3008122813C518677369 @default.
• W3008122813 hasConceptScore W3008122813C542102704 @default.
• W3008122813 hasConceptScore W3008122813C66402592 @default.
• W3008122813 hasLocation W30081228131 @default.
• W3008122813 hasLocation W30081228132 @default.
• W3008122813 hasOpenAccess W3008122813 @default.
• W3008122813 hasPrimaryLocation W30081228131 @default.
• W3008122813 hasRelatedWork W1538926071 @default.
• W3008122813 hasRelatedWork W1551461322 @default.
• W3008122813 hasRelatedWork W2100276986 @default.
• W3008122813 hasRelatedWork W2422749097 @default.
• W3008122813 hasRelatedWork W2528289822 @default.
• W3008122813 hasRelatedWork W2766225657 @default.
• W3008122813 hasRelatedWork W2914562313 @default.
• W3008122813 hasRelatedWork W2921866212 @default.
• W3008122813 hasRelatedWork W2951104962 @default.
• W3008122813 hasRelatedWork W2996665118 @default.
• W3008122813 hasRelatedWork W3005266363 @default.
• W3008122813 hasRelatedWork W3006387990 @default.
• W3008122813 hasRelatedWork W3022488852 @default.
• W3008122813 hasRelatedWork W3080989070 @default.
• W3008122813 hasRelatedWork W3082781197 @default.
• W3008122813 hasRelatedWork W3098567156 @default.
• W3008122813 hasRelatedWork W3144759542 @default.
• W3008122813 hasRelatedWork W3186164146 @default.
• W3008122813 hasRelatedWork W3194924591 @default.
• W3008122813 hasRelatedWork W980276176 @default.
• W3008122813 isParatext "false" @default.
• W3008122813 isRetracted "false" @default.
• W3008122813 magId "3008122813" @default.
• W3008122813 workType "dissertation" @default.