Abstract

Purpose - Social media is characterized by its volume, its speed of generation and its easy and open access; all this making it an important source of information that provides valuable insights. Content characteristics such as valence and emotions play an important role in the diffusion of information; in fact, emotions can shape virality of topics in social media. The purpose of this research is to fill the gap in event detection applied on online content by incorporating sentiment, more specifically strong sentiment, as main attribute in identifying relevant content.Design/methodology/approach - The study proposes a methodology based on strong sentiment classification using machine learning and an advanced scoring technique.Findings - The results show the following key findings: the proposed methodology is able to automatically capture trending topics and achieve better classification compared to state-of-the-art topic detection algorithms. In addition, the methodology is not context specific; it is able to successfully identify important events from various datasets within the context of politics, rallies, various news and real tragedies.Originality/value - This study fills the gap of topic detection applied on online content by building on the assumption that important events trigger strong sentiment among the society. In addition, classic topic detection algorithms require tuning in terms of number of topics to search for. This methodology involves scoring the posts and, thus, does not require limiting the number topics; it also allows ordering the topics by relevance based on the value of the score.Peer review - The peer review history for this article is available at: https://publons.com/publon/10.1108/OIR12-2019-0373


Authors

Daou, Hoda

Publons users who've claimed - I am an author

No Publons users have claimed this paper.

Contributors on Publons
  • 1 reviewer
  • pre-publication peer review (FINAL ROUND)
    Decision Letter
    2020/07/22

    22-Jul-2020

    Dear Daou, Hoda

    It is a pleasure to accept your manuscript OIR-12-2019-0373.R1, entitled "Sentiment of the Public: The Role of Social Media in Revealing Important Events" in its current form for publication in Online Information Review. Please note, no further changes can be made to your manuscript.

    Please go to your Author Centre at https://mc.manuscriptcentral.com/oir (Manuscripts with Decisions for the submitting author or Manuscripts I have co-authored for all listed co-authors) to complete the Copyright Transfer Agreement form (CTA). We cannot publish your paper without this.

    All authors are requested to complete the form and to input their full contact details. If any of the contact information is incorrect you can update it by clicking on your name at the top right of the screen. Please note that this must be done prior to you submitting your CTA.

    If you have an ORCID please check your account details to ensure that your ORCID is validated.

    By publishing in this journal your work will benefit from Emerald EarlyCite. As soon as your CTA is completed your manuscript will pass to Emerald’s Content Management department and be processed for EarlyCite publication. EarlyCite is the author proofed, typeset version of record, fully citable by DOI. The EarlyCite article sits outside of a journal issue and is paginated in isolation. The EarlyCite article will be collated into a journal issue according to the journals’ publication schedule.

    FOR OPEN ACCESS AUTHORS: Please note if you have indicated that you would like to publish your article as Open Access via Emerald’s Gold Open Access route, you are required to complete a Creative Commons Attribution Licence - CCBY 4.0 (in place of the standard copyright assignment form referenced above). You will receive a follow up email within the next 30 days with a link to the CCBY licence and information regarding payment of the Article Processing Charge. If you have indicated that you might be eligible for a prepaid APC voucher, you will also be informed at this point if a voucher is available to you (for more information on APC vouchers please see http://www.emeraldpublishing.com/oapartnerships

    Thank you for your contribution. On behalf of the Editors of Online Information Review, we look forward to your continued contributions to the Journal.

    Sincerely,

    Dr. Eugenia Siapera
    Co-Editor
    eugenia.siapera@ucd.ie

    Decision letter by
    Cite this decision letter
    Reviewer report
    2020/07/12

    The paper has been improved according to reviewers suggestions .

    Reviewed by
    Cite this review
    Reviewer report
    2020/06/02

    Review comments given earlier were addressed

    Reviewed by
    Cite this review
    Author Response
    2020/05/25

    We would like to express our deep gratitude towards Dr. Eugenia Siapera and for the two anonymous Reviewers for their clear, constructive, and insightful collective comments that were well aligned and that have enabled us to move towards an improved version of the paper that provides readers with a clearer and more detailed methodology and results and highlights its contribution and practicality. We were very excited and encouraged to work on this major revision especially that the reviewers highlighted the potential of the paper. Please find below our detailed response to the reviewers’ comments; we have re-numbered the comments to address each concern in detail. Kindly note that all edits done to the paper are in blue color in the revised version of the paper.

    Reviewer 1:

    Comment 1:
    Proposed ML technique can be clearly explained either in Figure or in text. It would give better understanding
    Response: We would like to thank the reviewer for this very important comment. Indeed, the section that explains the proposed ML technique was very brief and lacks details. Now that we read the reviewers’ concerns, we find it more appropriate to include more information in the article as it adds clarity. We added Section 3.2.1 that clearly describes how the ML model is built and also describes the other two algorithms shown in Figure 2, VADER and Sentistrength.

    Comment 2:
    Originality: Does the paper make a significant theoretical, empirical and/or methodological contribution to an area of importance, within the scope of the journal?: Yes, the author proposed a technique to detect trending topics using sentiment detection. Yes, the topic lies within the scope of journal
    Response: We would like to thank the reviewer for this positive comment.

    Comment 3:
    Relationship to Literature: Does the paper demonstrate an adequate understanding of the relevant literature in the field and cite an appropriate range of literature sources? Is any significant work ignored? Is the literature review up-to-date? Has relevant material published in Online Information Review been cited?: yes, the manuscript talked about the literature exhaustively and referred recent papers too.
    - However, Bing Liu's work was not referred in the work,
    - No citation is given from OIR journal
    - research gap can be clearly stated
    Response: The reviewer’s comment revealed very relevant research that needs to be added to the literature review. Bing Liu’s work is highly cited and definitely very important to any study in sentiment analysis. In addition, we found related articles published in this journal, Online Information Review. These publications are added to Chapter 2 of the new version of the article, with all changes highlighted in blue. Below is a list of the added publications:
    • B. Liu and L. Zhang. A Survey of Opinion Mining and Sentiment Analysis, pages 415–463. Springer US, Boston, MA, 2012. ISBN 978-1-4614-3223-4. doi: 10.1007/978-1-4614-3223-4 13. URL https: //doi.org/10.1007/978-1-4614-3223-4_13.
    • L. Zhang, S. Wang, and B. Liu. Deep learning for sentiment analysis: A survey. WIREs Data Mining and Knowledge Discovery, 8(4):e1253, 2018. doi: 10.1002/widm.1253. URL https://onlinelibrary.wiley. com/doi/abs/10.1002/widm.1253.
    • Y. Zhang, M. J. Er, R. Venkatesan, N. Wang, and M. Pratama. Sentiment classification using Comprehensive Attention Recurrent models. In 2016 International Joint Conference on Neural Networks (IJCNN), pages 1562–1569. IEEE, 2016. ISBN 978-1-5090-0620-5. URL http://dblp.uni-trier.de/db/conf/ijcnn/ ijcnn2016.html#ZhangEVWP16.
    • M. Abirami and A. Askarunisa. Sentiment analysis model to emphasize the impact of online reviews in healthcare industry. Online Information Review, 41:471–486, 2017.
    • Hung. Word of mouth quality classification based on contextual sentiment lexicons. Information Processing & Management, 53(4):751 – 763, 2017. ISSN 0306-4573. doi: https://doi.org/10.1016/j.ipm.2017.02.007. URL http://www.sciencedirect.com/science/article/pii/S0306457316301017.
    • J.-C. Na, T. T. Thet, and C. S. G. Khoo. Comparing sentiment expression in movie reviews from four online genres. Online Information Review, 34:317–338, 2010.

    At the end of Section 2, we highlight the research gap and objective behind our work:
    As mentioned in the Introduction, content characteristics such as sentiment, play an important role in the diffusion of information. And thus there is an intersection between research in sentiment analysis and topic identification, more specifically virality of topics. This has not been explored in previous work and thus, the purpose of this research is to fill the gap in event detection applied on online content by incorporating sentiment, more specifically strong sentiment, as main attribute in identifying relevant content.

    Comment 4:
    Methodology: Is the paper's argument built on an appropriate base of theory, concepts or other ideas? Has the research on which the paper is based been well designed? Are the methods employed appropriate and fully explained? Have issues of research ethics been adequately identified and addressed?: Methodology was explained well. The following may be considered to improve the quality of paper.
    Response: We would like to thank the reviewer for this positive comment and have carefully considered and applied the recommendations in comments 5 and 6 below.

    Comment 5:
    Suitable Research Questions can be framed with research objectives. It is not explicitly stated in the paper.
    Response: Indeed, it is very important to explicitly stress on the research objectives and this was only implicitly present in the previous version. We decided to add this in the Introduction where we highlight the gap in current studies that focus on sentiment analysis of social media posts, in paragraph 4. We move from current studies of sentiment analysis that simply provide descriptive analysis of events in social media content to our objective to fill such research gap by applying sentiment analysis in event detection for the purpose of identifying trending topics.
    “Content characteristics such as valence and emotions play an important role in the diffusion of information; in fact, emotions can shape virality of topics in social media. The purpose of this research is to fill the gap in event detection applied on online content by incorporating sentiment, more specifically strong sentiment, as main attribute in identifying trending topics.”

    Comment 6:
    Table 4 explains the list of words identified from the proposed methodology (sentiment detection). Most of the words are of type Nouns. How do the exhibit sentiment? Usually adjectives or verbs or adverbs give polarity (+ve or -ve)
    In other words, how does sentiment detection help in topic detection?
    Response: We would like to thank the reviewer for this question; this indicates that the article wasn’t clear about how the sentiment detection model is built. In the current version we added a detailed description about the sentiment detection model, explained in Section 3.2.1, Algorithm (1). This paragraph mentions that sentiment is computed based on word sentiment score including shifts and intensity, and also structural features such as punctuation. The aim of this work is to first detect posts that reflect strong sentiment, whether negative or positive. Second, these posts are used to identify important events that are shared on social media. The block diagram shown in Figure 1, summarizes the important steps of the suggested methodology. Table 4 shows the most frequent words of the detected topics after the last step of the methodology; which is detection of trending topics. In this table, we do not show the actual posts since (1) this is applied on a large number of posts, segmented per hour, and (2) the top words would better summarize and highlight the identified topic in these hourly segments.
    We added more explanation about Tables 3 and 4 to better explain these results. This can be found in the highlighted text in blue in Section 4.2.

    Comment 7:
    Results: For empirical papers - are results presented clearly and analysed appropriately?: Results may need to be improved based on the above comment. (Fig 4 and 5)
    Response: We hope that by
    (1) adding more clarification about the models used to answer comment 1;
    (2) explaining more the results, to answer comment 6 above; and (3) highlighting the fact and the proposed method is tested on many datasets, including recent ones, to answer comment 10;
    we have provided clear explanation on the methodology and results discussion. These results and analysis highlight the fact that the proposed framework is able to well detect trending topics, tested on different datasets.
    We also added Section 4.3, Discussion & Practical Implications, to further discuss the results and analyze their implications in a real setting. This section highlights the practicality of the proposed methodology in automatically detecting relevant events from large amounts of online posts.

    Comment 8:
    Figure 2 says RBF. What is RBF?
    Response: We would like to thank the reviewer for this comment that highlights the fact that the ML algorithm requires more details. We added Section 3.2.1 that clearly described how the ML model is built and describes the other two algorithms shown in Figure 2. In the description of Algorithm (1) ML model, RBF is mentioned; it refers to radial basis function.

    Comment 9:
    Figure 6 and 7 show the timeline of tweets. Whether it is the output of your work or descriptive analysis of dataset? It is not explained clearly
    Response: We thank the reviewer for pointing out the need of more clarification regarding the output of the suggested methodology. Figures 6 and 7 are indeed the output of the model showing the detected trending topics with respect to their corresponding actual events that their location in time. We added more information regarding these figures in Section 4.1.1 as follows:
    “The output of the model, presented in Table 3, is shown in the timeline of Figure 6 where the three main groups that cover these identified trending topics in terms of corresponding events, are shown in time.”[..]
    “Figure 7 shows the top 7 events, where similarly to the results shown for the Thai cave dataset, the combined score is displayed in descending order in the table. Similarly to the timeline in Figure 6, Figure 7 shows the timeline of the trending topics detected by the model, highlighting the actual events.”

    Comment 10:
    Implications for research, practice and/or society: Does the paper identify clearly any implications for research, practice and/or society? Does the paper bridge the gap between theory and practice? How can the research be used in practice (economic and commercial impact), in teaching, to influence public policy, in research (contributing to the body of knowledge)? What is the impact upon society (influencing public attitudes, affecting quality of life)? Are these implications consistent with the findings and conclusions of the paper?: yes, the work has an implication for the society. However, the dataset used was very old. The results would have been tested with recent dataset.
    Response: We thank the reviewer for this comment as it shows the need to stress more on the datasets used in testing and their recency.
    Evaluation is done in two ways: (1) quantitative that requires labeled datasets, and thus datasets (4) and (5) in Table 1 are used. These datasets are described under “Data for Trending Topic Detection: Quantitative Testing” in Section 4.1, and (2) qualitative that does not require labeled data and thus recent data is used, datasets (4) and (5) in Table 1. This data is described under “Data for Trending Topic Detection: Qualitative Testing” in Section 4.2. These datasets are streamed from Twitter in August 2017 (dataset 2) and July 2018 (dataset 3) and therefore recent. We acknowledge the importance of using recent data to confirm the quality of the technique and results and would like to thank the reviewer for highlighting this.
    We have added more details regarding which dataset is used in testing and stressed on its recency since it a very important criteria that confirms performance of the model. These are the sentences added to Sections 4.1 and 4.2:
    “It should be noted that these datasets are streamed in 2017 and 2018 and thus are very recent. The purpose is to test the model on recent events to make sure performance in maintained and the model is able to well identify trending topics.”
    [..] “This data is streamed from Twitter in July 2018 and contains around 6,600 tweets in total.”
    [..] “These events took place in August 2017 and data is streamed from Twitter with a total of around 1.2 million posts; more details are found in Section 3.1.”

    Comment 11:
    Quality of Communication: Does the paper clearly express its case, measured against the technical language of the fields and the expected knowledge of the journal's readership? Has attention been paid to the clarity of expression and readability, such as sentence structure, jargon use, acronyms, etc.: The manuscript is well written.
    - Anyhow, the author has to care for the spelling mistakes in line 210 (similar to), 215 (search)
    - Table caption has to be given above the table (Table 3)
    Response: We first would like to thank the author for saying that the paper is well written. We believe the reviewer wanted to refer to the error in Line 115 (Similarly to), however we were not able to locate the second error. We corrected the placement of the all tables’ captions. We also re-read the paper many times and made sure there are no typos and spelling mistakes.

    Comment 12:
    Reproducible Research: If appropriate, is sufficient information, potentially including data and software, provided to reproduce the results and are the corresponding datasets formally cited?: yes, dataset is cited.
    Response: We would like to thank the reviewer for the positive comment.

    Reviewer 2:

    Comment 1:
    The idea of the paper has a certain scientific value. However, more in-depth analysis and better presentation of the results might significantly improve the paper.
    Response: We would like to thank the reviewer for going through our article and sharing with us these valuable comments. This is very important to improve the clarity of the paper and better present the methodology and results and therefore highlight the contribution of our work.

    Comment 2:
    Originality: Does the paper make a significant theoretical, empirical and/or methodological contribution to an area of importance, within the scope of the journal?: This study is built on the assumption that important events can trigger strong sentiment, which seems reasonable and makes a relevant contribution within the scope of the journal.
    Response: We would like to thank the reviewer for the positive comment regarding the originality of our work.

    Comment 3:
    Relationship to Literature: Does the paper demonstrate an adequate understanding of the relevant literature in the field and cite an appropriate range of literature sources? Is any significant work ignored? Is the literature review up-to-date? Has relevant material published in Online Information Review been cited?: Yes, the paper demonstrate an adequate understanding of the relevant literature.
    Response: We would like to thank the reviewer for the positive comment and would also like to add that we added a few more article to answer Comment 3 of Reviewer 1. More improvements are added to this section and highlighted in blue in the new version of the article.

    Comment 4:
    Methodology: Is the paper's argument built on an appropriate base of theory, concepts or other ideas? Has the research on which the paper is based been well designed? Are the methods employed appropriate and fully explained? Have issues of research ethics been adequately identified and addressed?: The research on which the paper is based has been well designed, but not fully explained.
    Response:
    We understand and realize now that we have gone through the reviewers’ comments that the research work hasn’t been explained in detail. The paper lacks important information about the methodology and research objectives.
    To answer this comment, we have added in Paragraph 4 of the Introduction the research objectives behind our work. We move from current studies of sentiment analysis that simply provide descriptive analysis of events in social media content to our objective to fill such research gap by applying sentiment analysis in event detection for the purpose of identifying trending topics.
    “Content characteristics such as valence and emotions play an important role in the diffusion of information; in fact, emotions can shape virality of topics in social media. The purpose of this research is to fill the gap in event detection applied on online content by incorporating sentiment, more specifically strong sentiment, as main attribute in identifying trending topics.”

    In the revised version, we also highlight the research gap in the literature review and re-highlight the objective behind our work:
    As mentioned in the Introduction, content characteristics such as sentiment, play an important role in the diffusion of information. And thus there is an intersection between research in sentiment analysis and topic identification, more specifically virality of topics. This has not been explored in previous work and thus, the purpose of this research is to fill the gap in event detection applied on online content by incorporating sentiment, more specifically strong sentiment, as main attribute in identifying relevant content.

    In addition, we have modified Section 3 to include detailed description about the sentiment detection model, Section 3.2.1, Algorithm (1) and also describes the other two algorithms shown in Figure 2, Algorithm (2) VADER and Algorithm (3) Sentistrength. This section is essential to understand the research the methodology is based on and why we chose the specific ML model and its features.

    Comment 5:
    Results: For empirical papers - are results presented clearly and analysed appropriately?: The results are not very clearly presented.
    Response: We would like to thank the reviewer for highlighting this. This is an essential part of the article and we hope that by answering comment 6 we have added more clarity and have proven the quality of the work and thus its contribution to the research community.

    Comment 6:
    Discussion/Argument: Is the relation between any empirical findings and previous work discussed? Does the paper present a robust and coherent argument? To what extent does the paper engage critically with the literature and findings? Are theoretical concepts articulated well and used appropriately? Do the conclusions adequately tie together the other elements of the paper?: The theoretical concepts are articulated well and used appropriately, however the paper could benefit from an extended Discussion section that would better explain the findings and their value.
    Response: First, we added more explanation about Tables 3 and 4 to better explain these results. This can be found in the highlighted text in blue in Section 4.1.1. A sample of the added text is as follows:
    “It should be noted that this table shows the most frequent words of the detected topics after the last step of the methodology presented in Figure 1; which is detection of trending topics. In this table, we do not show the actual posts since (1) this is applied on a large number of posts, segmented per hour, and (2) the top words would better summarize and highlight the identified topic in these hourly segments.”
    We added more information regarding Figure 6 and 7 and show the results in Section 4.1.1 as follows:
    “The output of the model, presented in Table 3, is shown in the timeline of Figure 6 where the three main groups that cover these identified trending topics in terms of corresponding events, are shown in time.” [..] “Figure 7 shows the top 7 events, where similarly to the results shown for the Thai cave dataset, the combined score is displayed in descending order in the table. Similarly to the timeline in Figure 6, Figure 7 shows the timeline of the trending topics detected by the model, highlighting the actual events.”

    We also added a new Section, Section 4.2, that describes the results in detail and discusses their implications in terms of quality of the proposed methodology:
    “The methodology summarized above proved to be successful in identifying important events using an innovative way of extracting relevant tweets: sentiment analysis. This study is built on the assumption that important events can trigger strong sentiment among the society that can be detected from social media platforms. Nowadays, social media has become the most used outlet for sharing both personal and public information. This can be exploited for the purpose of automatically detecting important events.
    The suggested sentiment intensity classification model was able to reach better classification accuracy compared to the available SentiStrength tool and Vader toolbox. These results are displayed in Figure 2 and discussed in Section 3.2.2. This accuracy in detecting strong sentiment made it possible to flag important events that are reflected in Twitter posts using an advanced scoring technique.
    To test the capability of the suggested methodology in detecting important events, labeled datasets, more specifically datasets (4) and (5) of Table 1, are used and classification results of event detection are shown in Figures 4 and 5. The proposed sentiment based method is able to surpass the other algorithms (LDA, NMF and LSA), explained in Section 4.1, and gave best values of both Precision and Recall, and subsequently F1 Score. These supervised tests prove that the proposed method is able to provide solid classification of trending events using sentiment detection to identify relevant content.
    More tests are conducted on recent data streamed from Twitter, datasets (2) and (3). These tests are conducted to prove that the proposed methodology is able to provide reliable results from large amount of recent tweets, that contain important events. Detected events are scored using equation (1) in Section 3 and only top events are shown in the results of Tables 3 and 4 and Figures 6 and 7. Results show that top scored events match important actual events that occured during the streaming of both datasets. It should be noted that tweets are gouped per hour and each event is mapped to an hour in the overall timeline of the dataset. Timelines of the detected events highlight the relevancy of the identified events and therefore prove the reliability of the proposed method. It should be noted that dataset (2) contains 1.2 million tweets. The proposed method is able to sift through all these tweets and identify the ones that reflect important events that should be flagged. In addition the number of events identified depends on the chosen minimum value of the score. This value can be easily tuned depending on how many events we are aiming to detect and their intensity level. “

    Comment 7:
    Implications for research, practice and/or society: Does the paper identify clearly any implications for research, practice and/or society? Does the paper bridge the gap between theory and practice? How can the research be used in practice (economic and commercial impact), in teaching, to influence public policy, in research (contributing to the body of knowledge)? What is the impact upon society (influencing public attitudes, affecting quality of life)? Are these implications consistent with the findings and conclusions of the paper?: If properly presented and explained, this research has a potential to be used in practice.
    Response: The new version of the paper includes the edits described in the above answer and we believe that this has properly presented and explained the results of testing the methodology on multiple datasets. The new section presented above, Section 4.2, entitled Discussion & Practical Implications, highlights the potential of the proposed methodology and its practicality in a real setting, with real and recent datasets that could include millions of raw tweets.

    Comment 8:
    Quality of Communication: Does the paper clearly express its case, measured against the technical language of the fields and the expected knowledge of the journal's readership? Has attention been paid to the clarity of expression and readability, such as sentence structure, jargon use, acronyms, etc.: The examples of text in Table 2 seem inappropriate for serious publication.
    Response: We have carefully gone through the new version of the article and checked for readability and use of acronyms and jargon. We cleaned the examples shown in Table 2 and removed inappropriate content.

    Author response by


    Cite this author response
  • pre-publication peer review (ROUND 1)
    Decision Letter
    2020/04/26

    &PHPSESSID26-Apr-2020;

    Dear Dr. Daou,

    Manuscript ID OIR-12-2019-0373 entitled "Sentiment of the Public: The Role of Social Media in Revealing Important Events" which you submitted to Online Information Review has been reviewed. The comments of the reviewer(s) are included at the bottom of this letter.

    The reviewers have recommended that you make major revisions to your manuscript prior to it being considered for publication.

    Please read their suggestions and if you choose to prepare a revised manuscript ensure that any changes that you make to your manuscript are highlighted, as well as described in your response to reviewers.

    Please also ensure that in doing so your paper does not exceed the maximum word length of 10000 words and that it meets all the requirements of the author guidelines at http://www.emeraldinsight.com/products/journals/author_guidelines.htm?id=oir=ubl727mru90lg3hc8sa5p5qrt2."

    To revise your manuscript log into https://mc.manuscriptcentral.com/oir and enter your Author Centre, where you will find your manuscript title listed under "Manuscripts with Decisions". Under "Actions" click on "Create a Revision". Your manuscript number has been appended to denote a revision.

    You will be unable to make your revisions on the originally submitted version of the manuscript. Instead, revise your manuscript using a word processing program and save it on your computer. Please also highlight the changes to your manuscript within the document by using the track changes mode in MS Word or by using bold or coloured text.

    Once the revised manuscript is prepared you can upload it and submit it through your Author Centre.

    When submitting your revised manuscript, you will be able to respond to the comments made by the reviewer(s) in the space provided. You can use this space to document any changes you make to the original manuscript. In order to expedite the processing of the revised manuscript, please be as specific as possible in your response to the reviewer(s).

    IMPORTANT: Your original files are available to you when you upload your revised manuscript. Please delete any redundant files before completing the submission.

    Because we are trying to facilitate timely publication of manuscripts submitted to Online Information Review, your revised manuscript should be uploaded as soon as possible. If it is not possible for you to submit your revision in a reasonable amount of time, we may have to consider your paper as a new submission.

    To help support you on your publishing journey we have partnered with Editage, a leading global science communication platform, to offer expert editorial support including language editing and translation.
    If your article has been rejected or revisions have been requested, you may benefit from Editage’s services. For a full list of services, visit: authorservices.emeraldpublishing.com/
    Please note that there is no obligation to use Editage and using this service does not guarantee publication.

    Once again, thank you for submitting your manuscript to Online Information Review. I look forward to receiving your revision.

    Yours sincerely,

    Dr. Eugenia Siapera
    eugenia.siapera@ucd.ie

    Reviewer(s)' Comments to Author:
    Reviewer: 1

    Recommendation: Major Revision

    Comments:
    Proposed ML technique can be clearly explained either in Figure or in text. It would give better understanding

    Additional Questions:
    Originality: Does the paper make a significant theoretical, empirical and/or methodological contribution to an area of importance, within the scope of the journal?: Yes, the author proposed a technique to detect trending topics using sentiment detection. Yes, the topic lies within the scope of journal

    Relationship to Literature: Does the paper demonstrate an adequate understanding of the relevant literature in the field and cite an appropriate range of literature sources? Is any significant work ignored? Is the literature review up-to-date? Has relevant material published in Online Information Review been cited?: yes, the manuscript talked about the literature exhaustively and referred recent papers too.
    - However, Bing Liu's work was not referred in the work,
    - No citation is given from OIR journal
    - research gap can be clearly stated

    Methodology: Is the paper's argument built on an appropriate base of theory, concepts or other ideas? Has the research on which the paper is based been well designed? Are the methods employed appropriate and fully explained? Have issues of research ethics been adequately identified and addressed?: Methodology was explained well. The following may be considered to improve the quality of paper.

    Suitable Research Questions can be framed with research objectives. It is not explicitly stated in the paper.

    Table 4 explains the list of words identified from the proposed methodology (sentiment detection). Most of the words are of type Nouns. How do the exhibit sentiment? Usually adjectives or verbs or adverbs give polarity (+ve or -ve)

    In other words, how does sentiment detection help in topic detection?

    Results: For empirical papers - are results presented clearly and analysed appropriately?: Results may need to be improved based on the above comment. (Fig 4 and 5)

    Figure 2 says RBF. What is RBF?

    Figure 6 and 7 show the timeline of tweets. Whether it is the output of your work or descriptive analysis of dataset? It is not explained clearly

    Discussion/Argument: Is the relation between any empirical findings and previous work discussed? Does the paper present a robust and coherent argument? To what extent does the paper engage critically with the literature and findings? Are theoretical concepts articulated well and used appropriately? Do the conclusions adequately tie together the other elements of the paper?: yes, findings are compared. Anyhow, proposed methodology can be clearly explained in the paper. The paper says "score" has been used, but it is not shown,

    Implications for research, practice and/or society: Does the paper identify clearly any implications for research, practice and/or society? Does the paper bridge the gap between theory and practice? How can the research be used in practice (economic and commercial impact), in teaching, to influence public policy, in research (contributing to the body of knowledge)? What is the impact upon society (influencing public attitudes, affecting quality of life)? Are these implications consistent with the findings and conclusions of the paper?: yes, the work has an implication for the society. However, the dataset used was very old. The results would have been tested with recent dataset.

    Quality of Communication: Does the paper clearly express its case, measured against the technical language of the fields and the expected knowledge of the journal's readership? Has attention been paid to the clarity of expression and readability, such as sentence structure, jargon use, acronyms, etc.: The manuscript is well written.
    - Anyhow, the author has to care for the spelling mistakes in line 210 (similar to), 215 (search)
    - Table caption has to be given above the table (Table 3)

    Reproducible Research: If appropriate, is sufficient information, potentially including data and software, provided to reproduce the results and are the corresponding datasets formally cited?: yes, dataset is cited.

    Reviewer: 2

    Recommendation: Major Revision

    Comments:
    The idea of the paper has a certain scientific value. However, more in-depth analysis and better presentation of the results might significantly improve the paper.

    Additional Questions:
    Originality: Does the paper make a significant theoretical, empirical and/or methodological contribution to an area of importance, within the scope of the journal?: This study is built on the assumption that
    important events can trigger strong sentiment, which seems reasonable and makes a relevant contribution within the scope of the journal.

    Relationship to Literature: Does the paper demonstrate an adequate understanding of the relevant literature in the field and cite an appropriate range of literature sources? Is any significant work ignored? Is the literature review up-to-date? Has relevant material published in Online Information Review been cited?: Yes, the paper demonstrate an adequate understanding of the relevant literature.

    Methodology: Is the paper's argument built on an appropriate base of theory, concepts or other ideas? Has the research on which the paper is based been well designed? Are the methods employed appropriate and fully explained? Have issues of research ethics been adequately identified and addressed?: The research on which the paper is based has been well designed, but not fully explained.

    Results: For empirical papers - are results presented clearly and analysed appropriately?: The results are not very clearly presented.

    Discussion/Argument: Is the relation between any empirical findings and previous work discussed? Does the paper present a robust and coherent argument? To what extent does the paper engage critically with the literature and findings? Are theoretical concepts articulated well and used appropriately? Do the conclusions adequately tie together the other elements of the paper?: The theoretical concepts are articulated well and used appropriately, however the paper could benefit from an extended Discussion section that would better explain the findings and their value.

    Implications for research, practice and/or society: Does the paper identify clearly any implications for research, practice and/or society? Does the paper bridge the gap between theory and practice? How can the research be used in practice (economic and commercial impact), in teaching, to influence public policy, in research (contributing to the body of knowledge)? What is the impact upon society (influencing public attitudes, affecting quality of life)? Are these implications consistent with the findings and conclusions of the paper?: If properly presented and explained, this research has a potential to be used in practice.

    Quality of Communication: Does the paper clearly express its case, measured against the technical language of the fields and the expected knowledge of the journal's readership? Has attention been paid to the clarity of expression and readability, such as sentence structure, jargon use, acronyms, etc.: The examples of text in Table 2 seem inappropriate for serious publication.

    Decision letter by
    Cite this decision letter
    Reviewer report
    2020/04/21

    The idea of the paper has a certain scientific value. However, more in-depth analysis and better presentation of the results might significantly improve the paper.

    Reviewed by
    Cite this review
    Reviewer report
    2020/01/26

    Proposed ML technique can be clearly explained either in Figure or in text. It would give better understanding

    Reviewed by
    Cite this review
All peer review content displayed here is covered by a Creative Commons CC BY 4.0 license.