Multimodal Self-Assessed Personality Prediction in the Wild

Kamisaka, Daisuke; Ishikawa, Yuichi

doi:10.1145/3395035.3425260

Cited by 3 publications

(11 citation statements)

References 22 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…To our knowledge, our previous work [14] is only an exception that examined a multimodal approach using both online service logs and visual data for personality prediction. Assuming that data volume of online service log is much larger than that of visual data, our previous approach used online service log for training a personality prediction model and used this model to predict personalities of customers who have only visual data (offline customers).…”

mentioning

confidence: 99%

“…Assuming that data volume of online service log is much larger than that of visual data, our previous approach used online service log for training a personality prediction model and used this model to predict personalities of customers who have only visual data (offline customers). To do so, in [14], we introduced a feature projection model that learns correlation between the two modalities from customers who have both online service logs and visual data (hybrid customers). Using the model, features of visual data of the offline customers were projected onto pseudo online service logs, which were then input to the personality prediction model.…”

mentioning

confidence: 99%

“…Although [14] improved prediction accuracy for the offline customers in comparison with ordinary unimodal approaches, two issues remain: (a) In principle, [14] is not effective if data volume of a projected (target) modality is smaller than that of an original (source) modality. Therefore, customers who have only online service logs (online customers) were out of scope of [14], though such customers account for large volume of customer base in today's business. (b) Even for the offline customers, accuracy improvement was marginal due to limited projection performance.…”

mentioning

confidence: 99%

“…In this paper, we proposed a multimodal approach to predict customers' Big Five [10] personalities, the most widely used personality model that consists of Openness, Conscientiousness, Extraversion, Agreeableness and Neuroticism. We significantly extends [14] to address (a) and (b). For (a), by a "self-feature fusion" technique, the approach studied in this paper covers both the online and the offline customers in its scope.…”

mentioning

confidence: 99%

“…This approach is effective regardless of whether data volume of one modality is larger than that of the other modality. To address (b), we examined two different methods that were not investigated in [14] for better feature projection: a model-based method and a model-free method. The former uses a regression model to generate pseudo features.…”

mentioning

confidence: 99%

See 4 more Smart Citations

Personality Prediction with Cross-Modality Feature Projection

Kamisaka

Ishikawa

2021

Proceedings of the 2021 International Conference on Multimodal Interaction

Self Cite

View full text Add to dashboard Cite

In this paper, we propose an approach to predict customers' personalities leveraging two modalities of customers' data: (a) service usages logs of online services and (b) visual data collected in physical stores by surveillance cameras (e.g., gait and whereabouts). A number of companies provide services via online and offline nowadays, thus need to serve two different kinds of customers: "online customers, " who use services completely online and have only (a); and "offline customers, " who use only physical stores and have only (b). To improve personality prediction accuracy for these customers, our approach generates pseudo features of a non-existent modality from the other modality that the customers actually have (i.e., feature projection; e.g., generate pseudo visual data of the online customers from their real online service logs), and uses both pseudo and real features to predict their personalities. The evaluation using real-world data of a mobile carrier's customers showed that our approach predicted personality more accurately than an ordinary unimodal approach for both online and offline customers. We also examined importance of the feature projection and compared two different projection methods. CCS CONCEPTS• Computing methodologies → Machine learning; • Humancentered computing → Human computer interaction (HCI).

show abstract

mentioning

confidence: 99%

mentioning

confidence: 99%

mentioning

confidence: 99%

mentioning

confidence: 99%

mentioning

confidence: 99%

See 3 more Smart Citations

Personality Prediction with Cross-Modality Feature Projection

Kamisaka

Ishikawa

2021

Proceedings of the 2021 International Conference on Multimodal Interaction

Self Cite

View full text Add to dashboard Cite

show abstract

Wearable Internet of Things Gait Sensors for Quantitative Assessment of Myers–Briggs Type Indicator Personality

Zhao,

Xing,

Wang

et al. 2023

Advanced Intelligent Systems

View full text Add to dashboard Cite

Gait is a typical habitual human behavior and manifestation of personality. The unique properties of individual gaits may offer important clues in the assessment of personality. However, assessing personality accurately through quantitative gait analysis remains a daunting challenge. Herein, targeting young individuals, standardized gait data are obtained from 114 subjects with a wearable gait sensor, and the Myers–Briggs Type Indicator (MBTl) personality scale is used to assess their corresponding personality types. Artificial intelligence algorithms are used to systematically mine the relationship between gaits and 16 personality types. The work shows that gait parameters can indicate the personality of a subject from the four MBTI dimensions of E‐l, S‐N, T‐F, and J‐P with a concordance rate as high as 95%, 96%, 91%, and 91%, respectively. The overall measurement accuracy for the 16 personality types is 88.16%. Moreover, a personality tracking experiment on all the subjects after one year to assess the stability of their personality is also conducted. This research, which is based on a smart wearable Internet of Things gait sensor, not only establishes a new connection between behavioral analysis and personality assessment but also provides a set of accurate research tools for the quantitative assessment of personality.

show abstract

The Influence of Personalization on Consumer Satisfaction

Casaca,

Miguel

2024

Advances in Marketing, Customer Relationship Management, and E-Services

View full text Add to dashboard Cite

In today's digital age, where consumers are inundated with a barrage of information and choices, the ability to tailor marketing efforts to individual preferences has become a powerful tool. This study aims to understand how personalization can influence consumer satisfaction. To achieve this goal, the authors carried out a systematic review of the literature, based on 79 articles published in the WoS™ database between 2014 and 2023. The R-Tool “Biblioshiny for Bibliometrix” was used to perform a comprehensive bibliometrics analysis, based on evaluative and relational bibliometrics techniques, which allow them to analyze the knowledge structure in terms of three different structures: conceptual, intellectual, and social. They concluded that personalization has emerged as a cornerstone of modern marketing strategies, reshaping the way businesses connect with their customers. The impact of personalization on customer satisfaction is profound, leading to enhanced customer experiences, increased engagement, improved customer retention, and the building of trust and credibility.

show abstract

Multimodal Self-Assessed Personality Prediction in the Wild

Cited by 3 publications

References 22 publications

Personality Prediction with Cross-Modality Feature Projection

Personality Prediction with Cross-Modality Feature Projection

Wearable Internet of Things Gait Sensors for Quantitative Assessment of Myers–Briggs Type Indicator Personality

The Influence of Personalization on Consumer Satisfaction

Contact Info

Product

Resources

About