Open AccessImplementation of social media mining for decision making in product planning based on topic modeling and sentiment analysis
Author(s) -
Mohammad Isa Irawan,
R Wijayanto,
Muhammad Luthfi Shahab,
Nurul Hidayat,
Alvida Mustika Rukmi
Publication year - 2020
Publication title -
journal of physics. conference series
Language(s) - English
Resource type - Journals
SCImago Journal Rank - 0.21
H-Index - 85
eISSN - 1742-6596
pISSN - 1742-6588
DOI - 10.1088/1742-6596/1490/1/012068
Subject(s) - sentiment analysis , competitor analysis , lexicon , social media , computer science , product (mathematics) , service (business) , field (mathematics) , topic model , data science , meaning (existential) , latent semantic analysis , marketing , artificial intelligence , world wide web , business , psychology , geometry , mathematics , pure mathematics , psychotherapist
The development of information and communication technology, especially on the social media field, brings a wide change in product planning in company. At this time, a company can identify the opportunity for product planning based on customers’ opinion through Twitter’s postings. This opportunity can be used to increase the competitiveness and defend from the competitors. The main method that is used in this research is social media mining based on topic modeling and sentiment analysis. The topic that is widely discussed by the customers is identified as the importance degree and the result of sentiment analysis is identified as the satisfaction degree. We successfully apply topic modeling with Latent Semantic Analysis and K-Means cluster and sentiment analysis with lexicon dictionary from Hutto and Gilbert. Using McDonald’s 2000 tweets, it can be concluded that “service in the morning” has the highest opportunity degree and it is categorized at under-served thing. It gives us a meaning that “service in the morning” is one of the service which has a great chance at the market.