Siti Nur Aisyah Binti Anuar, <br/><br/>
Identifying potential customers using  graph social media analytics / 
Siti Nur Aisyah Binti Anuar 
 - xii , 81 pages :  Illustration (some colour) ;  1 CD-ROM. 
<br/><br/> Center for Mathematical Sciences 
<br/><br/>Bachelor of Applied Science In Data Analytics With Honour -- Universiti Malaysia Pahang – 2023 
<br/><br/>Includes bibliographical references 
<br/><br/> In today's digital era, businesses try to find new clients in many ways. This study offers  approaches that use graph social media analytics to identify potential clients for the  product Soft Pinch Liquid Blush. The dataset used in this study was gathered from Twitter  search queries and contains parameters such as date, time, username identification, text,  language, hashtags, reply count, retweet count, like count, quote count, discussion  identification, retweet tweet, quoted tweet, reply identification, user and location. The  main objective of this study is to discover potential customers for the product Soft Pinch  Liquid Blush using graph social media analytics, as well as find significant sources and  nodes relevant to the product. The analysis starts by building a graph network with the  Source and Target columns, where the Source column represents people who tweeted  about the product and the Target column represents people who were referenced or  reacted to a tweet, indicating prospective interest. The number of likes, retweets and  sentiment values are then used to generate influence scores. Voterank and centrality  metrics are also used to evaluate node significance. To find communities in the network,  three graph community techniques which are Louvain, Clauset-Newman-Moore greedy  modularity and label propagation are used. The community results were compared using  modularity, coverage and performance. Based on the result, node  “SGomezNewsCOMsNode” has the highest influence score for both the number of likes  and retweets by considering sentiment value. Node “rarebeauty” was the most influential  node based on voterank and centrality metrics. Louvain and Clauset-Newman-Moore  algorithms appear to outperform label propagation in terms of modularity and  performance score of community structure. However, label propagation outperforms  Louvain and Clauset-Newman-Moore algorithms in terms of coverage. The study  concludes that Louvain and Clauset-Newman-Moore are the suitable algorithms in this  study, even though the modularity value was low. For future research, it recommended  to add more edges between nodes to increase the overall connection of the network and  do network pre-processing such as noise removal, sparsity reduction and edge weight  normalization to enhance the modularity score. 
<br/><br/><label>ISBN: </label>THE0010040 (Local) 
<br/><br/><label>Subjects--Corporate Names: </label><br/>Center for Mathematical Sciences--Dissertations
<br/><br/><label>Subjects--Topical Terms: </label><br/>Universities and colleges--Dissertations<br/>Final Year Report--Dissertations