Social media and online reviews have changed customer behavior when buying fashion products online. Online customer reviews also provide opportunities for businesses to deliver improved customer experiences. This study aims to develop fashion style models, based on online customer reviews from e-commerce systems to analyze customer preferences. Topic Modeling with Latent Dirichlet Allocation (LDA) was performed on a large collection of online customer reviews in different categories to investigate customer preferences by building fashion style models in a semantic space. Online product review data from Amazon, one of the leading online shopping websites globally, and Rakuten, one of the representative online shopping websites in Japan, were used to reveal the hidden topics in the review texts. The obtained topic definitions were manually examined, and the results were used to build computational models reflecting semantic relationships. The obtained fashion style models can potentially help marketing and product design specialists better understand customer preferences in the e-commerce fashion industry.

Non-Linguistic Utterances (NLUs), produced for popular media, computers, robots, and public spaces, can quickly and wordlessly convey emotional characteristics of a message. They have been studied in terms of their ability to convey affect in robot communication. The objective of this research is to develop a model that correctly infers the emotional Valence and Arousal of an NLU. On a Likert scale, 17 subjects evaluated the relative Valence and Arousal of 560 sounds collected from popular movies, TV shows, and video games, including NLUs and other character utterances. Three audio feature sets were used to extract features including spectral energy, spectral spread, zero-crossing rate (ZCR), Mel Frequency Cepstral Coefficients (MFCCs), and audio chroma, as well as pitch, jitter, formant, shimmer, loudness, and Harmonics-to-Noise Ratio, among others. After feature reduction by Factor Analysis, the best-performing models inferred average Valence with a Mean Absolute Error (MAE) of 0.107 and Arousal with MAE of 0.097 on audio samples removed from the training stages. These results suggest the model infers Valence and Arousal of most NLUs to less than the difference between successive rating points on the 7-point Likert scale (0.14). This inference system is applicable to the development of novel NLUs to augment robot-human communication or to the design of sounds for other systems, machines, and settings.

No abstract

Voting advice applications (VAA) allow potential voters to compare their own policy positions to political parties running for an election. One of the key design elements of a VAA are the policy statements representing the political space covered by political parties. VAA designers face the challenge of coming up with policy statements in a short time frame. Even with medium-sized corpora of texts such as party manifestos, the formulation and selection of policy statements serving as a stimulus in the VAA is a tedious and time-consuming task. In addition, there is the risk of human selection bias. This study proposes a system to aid VAA designers in policy statement selection and formulation. The system uses the BERT language model with semantic similarity calculation to mine party manifesto sentences that are relevant to already existing VAA statements. For the experiments, VAA statements stemming from the 2021 elections and party manifestos issued for the previous two Japanese elections were used. To expand the policy space, VAA statements from the 2019 European Parliament elections were added. Results show that the proposed system is able to analyze large amounts of text in a short time, and mines text that provides practical support for designing and improving VAAs.

Since 2015 all citizens in Taiwan and since 2018 also residents can use the online platform called "Join". The platform allows registered users to propose, discuss and review governmental policies. The ongoing practice currently makes Join one of the most innovative and successful cases of digital policy co-creation worldwide. However, due to the language barrier little is known about its contents. Internationally available research results are scarce. This article provides an overview of the platform's functionalities as well as an overview of the research published to date. In addition, a first descriptive inroad to online petition dynamics is made. The case studies are based on the dataset available on the government's Open Data portal. The goal of this paper is to lay the groundwork and provide the context for a more comprehensive quantitative analysis of online petition signing dynamics in Taiwan.