Building a Multimodal Classifier of Email Behavior: Towards a Social Network Understanding of Organizational Communication
Within organizational settings, communication dynamics are influenced by various factors, such as email content, historical interactions, and interpersonal relationships. We introduce the Email MultiModal Architecture (EMMA) to model these dynamics and predict future communication behavior. EMMA use...
| Main Authors: | , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2023-12-01
|
| Series: | Information |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2078-2489/14/12/661 |
| _version_ | 1827574590246748160 |
|---|---|
| author | Harsh Shah Kokil Jaidka Lyle Ungar Jesse Fagan Travis Grosser |
| author_facet | Harsh Shah Kokil Jaidka Lyle Ungar Jesse Fagan Travis Grosser |
| author_sort | Harsh Shah |
| collection | DOAJ |
| description | Within organizational settings, communication dynamics are influenced by various factors, such as email content, historical interactions, and interpersonal relationships. We introduce the Email MultiModal Architecture (EMMA) to model these dynamics and predict future communication behavior. EMMA uses data related to an email sender’s social network, performance metrics, and peer endorsements to predict the probability of receiving an email response. Our primary analysis is based on a dataset of 0.6 million corporate emails from 4320 employees between 2012 and 2014. By integrating features that capture a sender’s organizational influence and likability within a multimodal structure, EMMA offers improved performance over models that rely solely on linguistic attributes. Our findings indicate that EMMA enhances email reply prediction accuracy by up to 12.5% compared to leading text-centric models. EMMA also demonstrates high accuracy on other email datasets, reinforcing its utility and generalizability in diverse contexts. Our findings recommend the need for multimodal approaches to better model communication patterns within organizations and teams and to better understand how relationships and histories shape communication trajectories. |
| first_indexed | 2024-03-08T20:40:19Z |
| format | Article |
| id | doaj.art-eac3fd54b5de404096ecfadc5fddea14 |
| institution | Directory Open Access Journal |
| issn | 2078-2489 |
| language | English |
| last_indexed | 2024-03-08T20:40:19Z |
| publishDate | 2023-12-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Information |
| spelling | doaj.art-eac3fd54b5de404096ecfadc5fddea142023-12-22T14:15:56ZengMDPI AGInformation2078-24892023-12-01141266110.3390/info14120661Building a Multimodal Classifier of Email Behavior: Towards a Social Network Understanding of Organizational CommunicationHarsh Shah0Kokil Jaidka1Lyle Ungar2Jesse Fagan3Travis Grosser4Department of Electrical & Electronics Engineering, Birla Institute of Technology Pilani, Rajasthan 333031, IndiaDepartment of Communications and New Media, National University of Singapore, Singapore 119077, SingaporeDepartment of Computer and Information Sciences, University of Pennsylvania, Philadelphia, PA 19104, USAThe Business School, University of Exeter, Exeter EX4 4PY, UKThe School of Business, University of Connecticut, Storrs, CT 06269, USAWithin organizational settings, communication dynamics are influenced by various factors, such as email content, historical interactions, and interpersonal relationships. We introduce the Email MultiModal Architecture (EMMA) to model these dynamics and predict future communication behavior. EMMA uses data related to an email sender’s social network, performance metrics, and peer endorsements to predict the probability of receiving an email response. Our primary analysis is based on a dataset of 0.6 million corporate emails from 4320 employees between 2012 and 2014. By integrating features that capture a sender’s organizational influence and likability within a multimodal structure, EMMA offers improved performance over models that rely solely on linguistic attributes. Our findings indicate that EMMA enhances email reply prediction accuracy by up to 12.5% compared to leading text-centric models. EMMA also demonstrates high accuracy on other email datasets, reinforcing its utility and generalizability in diverse contexts. Our findings recommend the need for multimodal approaches to better model communication patterns within organizations and teams and to better understand how relationships and histories shape communication trajectories.https://www.mdpi.com/2078-2489/14/12/661emailorganizationsocial network analysistext classificationcomputational linguisticstransformers |
| spellingShingle | Harsh Shah Kokil Jaidka Lyle Ungar Jesse Fagan Travis Grosser Building a Multimodal Classifier of Email Behavior: Towards a Social Network Understanding of Organizational Communication Information organization social network analysis text classification computational linguistics transformers |
| title | Building a Multimodal Classifier of Email Behavior: Towards a Social Network Understanding of Organizational Communication |
| title_full | Building a Multimodal Classifier of Email Behavior: Towards a Social Network Understanding of Organizational Communication |
| title_fullStr | Building a Multimodal Classifier of Email Behavior: Towards a Social Network Understanding of Organizational Communication |
| title_full_unstemmed | Building a Multimodal Classifier of Email Behavior: Towards a Social Network Understanding of Organizational Communication |
| title_short | Building a Multimodal Classifier of Email Behavior: Towards a Social Network Understanding of Organizational Communication |
| title_sort | building a multimodal classifier of email behavior towards a social network understanding of organizational communication |
| topic | email organization social network analysis text classification computational linguistics transformers |
| url | https://www.mdpi.com/2078-2489/14/12/661 |
| work_keys_str_mv | AT harshshah buildingamultimodalclassifierofemailbehaviortowardsasocialnetworkunderstandingoforganizationalcommunication AT kokiljaidka buildingamultimodalclassifierofemailbehaviortowardsasocialnetworkunderstandingoforganizationalcommunication AT lyleungar buildingamultimodalclassifierofemailbehaviortowardsasocialnetworkunderstandingoforganizationalcommunication AT jessefagan buildingamultimodalclassifierofemailbehaviortowardsasocialnetworkunderstandingoforganizationalcommunication AT travisgrosser buildingamultimodalclassifierofemailbehaviortowardsasocialnetworkunderstandingoforganizationalcommunication |