| Autor: |
Saptarsi Goswami, Sourav Malakar, Amlan Chakrabarti |
| Rok vydání: |
2017 |
| Předmět: |
|
| Zdroj: |
Lecture Notes in Networks and Systems ISBN: 9789811039522 |
| Popis: |
Twitter is one of the most popular online social networking and micro-blogging service that enables its users to post and share text-based messages called Tweets. The data generated daily in terms of tweets are enormous and represents a rich source of information. To elicit actionable intelligence, various natural language processing (NLP) and text mining techniques are applied. Detecting of trends from twitters represents an important set of problems with a wide variety of applications and has huge appeal to diverse communities. In this paper, a simple trend detection technique based on term frequency has been proposed. In the first step, term document matrix of the tweet stream is created and top words are identified. The top word list is dynamically updated based on new streams. Time series is generated for the top words. Trends of the words are detected using Mann–Kendall non-parametric test. The method has been applied on few topical twitter datasets and proved to be quite effective. |
| Databáze: |
OpenAIRE |
| Externí odkaz: |
|
