Big Data Text Analysis
A free Windows program for keyword, issue, time series, sentiment, gender and content analyses of (mainly) social media texts. *download*
Versions before 2 March 2020 report incorrect dates (1899) for texts from 2020.
Academic researchers and students can use Academic Research Mozdeh
For updates, follow @Mozdeh4
These options work for all languages with spaces between words. Special instructions for Japanese and Chinese.
Thelwall, M. (2021). Word association thematic analysis: A social media text exploration strategy. San Rafael, CA: Morgan & Claypool. [A method to analyse text for themes with Mozdeh.]
Thelwall, M. (2018). Social web text analytics with Mozdeh. University of Wolverhampton. [free short overview book]
Mozdeh was used to collect and analyse data for the following.
Thelwall, M., Thelwall, S. & Fairclough, R. (in press). Male, female, and nonbinary differences in UK Twitter self-descriptions: A fine-grained systematic exploration. Journal of Data and Information Science.
Thelwall, M., Makita, M., Mas-Bleda, A., & Stuart, E. (2021). “My ADHD hellbrain”: A Twitter data science perspective on a behavioural disorder. Journal of Data and Information Science, 6(1).
Thelwall, S. & Thelwall, M. (in press). Anthropomorphizing atopy: Tweeting about eczema. Journal of the Dermatology Nurses' Association.
Potts, G., & Radford, D. R. (2019). #Teeth&Tweets: the reach and reaction of an online social media oral health promotion campaign. British Dental Journal, 227(3), 217-222.
Thelwall, M. (2018). Can museums find male or female audiences online with YouTube? Aslib Journal of Information Management, 70(5), 481-497.
Thelwall, M. & Mas-Bleda, A. (2018). YouTube science channel video presenters and comments: Female friendly or vestiges of sexism? Aslib Journal of Information Management, 70(1), 28-46.
Thelwall, M. (2018). Can social news websites pay for content and curation? The SteemIt cryptocurrency model. Journal of Information Science, 44(6), 736–751.
Ahmed, W. (2018). Using Social Media Data for Research: An Overview of Tools. Journal of Communication Technology, 1(1), 77-94.
Thelwall, M. (2018). Social media analytics for YouTube comments: Potential and limitations. International Journal of Social Research Methodology, 21(3), 303-316. doi:10.1080/13645579.2017.1381821 [ local copy]
Holmberg, K., & Hellsten, I. (2014). Analyzing the climate change debate on Twitter: content and differences between genders. In Proceedings of the 2014 ACM conference on Web science (pp. 287-288). ACM.
Terlumun, I. T., Appollm, Y. I., Ibrahim, F. J., Mamman, F. S., Yusuf, A. K., & Ibrahim, A. H. (2018). Determining the Effectiveness of YouTube Videos in Teaching and Learning with Mozdeh Algorithm. International Journal of Education and Evaluation.
Thelwall, M., & Cugelman, B. (2017). Monitoring Twitter strategies to discover resonating topics: The case of the UNDP. El profesional de la información.
Thelwall, M., Buckley, K., & Paltoglou, G. (2011). Sentiment in Twitter events. Journal of the American Society for Information Science and Technology, 62(2), 406-418.
Thelwall, M. (2008). No place for news in social network web sites? Online Information Review, 32(6), 726-744.
Sentiment and retweet/reviews/citation graphs and the top of the word frequency table.
Mozdeh can produce a time series graph of the volume of texts for your topic. The graph below is a section of a screenshot showing the hourly volume of tweeting for a corpus of tweets related to the 2011 UK Riots in 2011.
Mozdeh can produce a time series graph of the percentage of texts matching a query for your topic. The graph below is a section of a screenshot showing the hourly percentage of tweets mentioning police in a UK Riots 2011 corpus.
Mozdeh can produce a time series graph of the average positive and negative sentiment of texts for your whole topic or just the texts matching a query for your topic. The graph below is a section of a screenshot showing the hourly average sentiment of tweets mentioning police in a UK Riots 2011 corpus.
Mozdeh can search for texts matching a query for your topic. The picture below is a section of a screenshot showing some of the results of a search for Wolverhampton in a UK Riots 2011 Twitter corpus.
If you can't use Windows, then you might try COSMOS for Mac/Linux or investigate this list of social media software.
|Made by the Statistical Cybermetrics Research Group at the University of Wolverhampton during the CREEN and CyberEmotions EU projects.|