Analyzing User Digital Emotions from a Holy versus Non-Pilgrimage City in Saudi Arabia on Twitter Platform
Round 1
Reviewer 1 Report
This study presents that the user data available on Twitter has the potential to showcase the contrasting emotions of people residing in a pilgrim city versus the ones in a normal region.
The main aim of the study should be clear, why is important to understand people emotion from a Holy versus Non-pilgrimage City.
Is the tweets only collected from Saudi Arabia? Is different dialects are covered?
Why only twitter has been used? I would recommend to compare the current results with Facebook and other social media platforms.
How many percentage of people in twitter actively used twitter?
After data pre-praration, is there any feature engineering has been done?
Why only MECCA used? Medina is not religious city?
I would recommend to update the related work with following references:
Alqarafi, A.S., Adeel, A., Gogate, M., Dashitpour, K., Hussain, A. and Durrani, T., 2017, July. Toward’s Arabic multi-modal sentiment analysis. In International Conference in Communications, Signal Processing, and Systems (pp. 2378-2386). Springer, Singapore.
Ghallab, A., Mohsen, A. and Ali, Y., 2020. Arabic sentiment analysis: A systematic literature review. Applied Computational Intelligence and Soft Computing, 2020.
Hawalah, A., 2019. Semantic ontology-based approach to enhance Arabic text classification. Big Data and Cognitive Computing, 3(4), p.53.
Author Response
Author's Reply to the Review Report (Reviewer 1)
Comment: Is the tweets only collected from Saudi Arabia? Is different dialects are covered?
Response: Yes, the tweets have been collected from the two cities of Saudi Arabia only using the geolocation coordinated (Riyadh (45.04,24.01,47.91,26.33) and Mecca (38.66,18.1,43.67,23.97) using Klokantech bounding box tool [26].). The user tweets were collected based on their locations and language, excluding retweets. We particularly focused on all the possible Saudi dialects including Najdi Arabic, Gulf Arabic, etc.
Comment: Why only twitter has been used? I would recommend comparing the current results with Facebook and other social media platforms.
Response: Thank you very much for your valuable feedback. The proposed study is more like extraction of sentiments (emotions) from the text. The Twitter network seemed one of the main sources of text where users express their feeling in just 280 characters. The other social networking platforms like Facebook hold other user content (audios, videos, images in almost equal ratio) as well. However, in our future work, we can include all types of media content and will try to compare the results with other social media platforms as well.
Comment: How many percentage of people in twitter actively used twitter?
Response: As per the report [1] there are 192 million daily active users on Twitter and 13 million daily active users in Saudi Arabia [2]. In the collected dataset we did not specifically estimate the activeness of the users. However, we harvested the data from selected Twitter profiles for a span of 1.5 months and collected on an average 20 Tweets per user.
Comment: After data pre-praration, is there any feature engineering has been done?
Response: After data pre-preparation, we have employed Plutchik’s emotions wheel [34] to extracted the 8 emotion category-related words from the user tweets and used these emotion words as features in our emotion mining experiments. These features can further be used to distinguish the users from two different cities.
Comment: Why only MECCA used? Medina is not religious city?
Response: Yes, Medina is also a religious city. The proposed study aims at showing the potential of social media data shared by users in uncovering the impact of user’s surroundings on their mental health, therefore to analyze the user content from two different cites in Saudi Arabia we choose one of the holy cities (out of Mecca and Medina) and Riyad as a non-holy (where Muslims are not necessarily required to visit during Haj or Umrah) city.
Comment: I would recommend to update the related work with following references:
Response: The related work section of the paper has been updated as per the new references. Thank you very much for providing very related references for the proposed study.
All the authors would like to thank the reviewer for valuable feedback and necessary comments to enhance the quality of the current study.
[1] https://www.oberlo.in/blog/twitter-statistics#:~:text=There%20are%20192%20million%20daily,on%20Twitter%20is%203.39%20minutes.
[2] https://www.statista.com/statistics/242606/number-of-active-twitter-users-in-selected-countries/
Author Response File: Author Response.docx
Reviewer 2 Report
The study presented seems to me to be of the highest interest as it allows us to understand sociological factors that would otherwise be difficult to evaluate. The use of tools such as those proposed by the authors would save a great deal of money in sociological studies and would make it possible to know the state of the population almost immediately.
In situations of catastrophe or important social changes, it could be of great help.
I would accept the work in its present version.
Author Response
Comment: The study presented seems to me to be of the highest interest as it allows us to understand sociological factors that would otherwise be difficult to evaluate. The use of tools such as those proposed by the authors would save a great deal of money in sociological studies and would make it possible to know the state of the population almost immediately.
In situations of catastrophe or important social changes, it could be of great help.
I would accept the work in its present version.
Response: All the authors of this study would like to thank the reviewer for their wonderful and praising comments. We also would like to thank you for providing us an idea to convert this experimental study into a workable tool to understand and estimate the social factors and assist a variety of professionals including sociologists, psychiatrists, clinicians, etc. in their work.
Author Response File: Author Response.docx