{"id":1062,"date":"2026-11-02T11:56:05","date_gmt":"2026-11-02T02:56:05","guid":{"rendered":"https:\/\/www.shimonoseki-cu.ac.jp\/sdgs\/?p=1062"},"modified":"2026-11-02T11:56:05","modified_gmt":"2026-11-02T02:56:05","slug":"ai%e3%81%af%e5%b0%8f%e8%aa%ac%e3%81%ae%e3%80%8c%e6%82%b2%e3%81%97%e3%81%84%e3%80%8d%e3%82%92%e3%81%a9%e3%81%86%e8%aa%ad%e3%81%bf%e5%8f%96%e3%82%8b%ef%bc%9f-%e7%99%bd%e6%bf%b5%e6%95%99%e6%8e%88","status":"publish","type":"post","link":"https:\/\/www.shimonoseki-cu.ac.jp\/sdgs\/2026\/11\/02\/ai%e3%81%af%e5%b0%8f%e8%aa%ac%e3%81%ae%e3%80%8c%e6%82%b2%e3%81%97%e3%81%84%e3%80%8d%e3%82%92%e3%81%a9%e3%81%86%e8%aa%ad%e3%81%bf%e5%8f%96%e3%82%8b%ef%bc%9f-%e7%99%bd%e6%bf%b5%e6%95%99%e6%8e%88\/","title":{"rendered":"AI\u306f\u5c0f\u8aac\u306e\u300c\u60b2\u3057\u3044\u300d\u3092\u3069\u3046\u8aad\u307f\u53d6\u308b\uff1f \u767d\u6ff5\u6559\u6388\u3089\u304c\u56fd\u969b\u4f1a\u8b70ICECCME 2026\u3067\u7814\u7a76\u6210\u679c\u3092\u767a\u8868"},"content":{"rendered":"\n

\u4e0b\u95a2\u5e02\u7acb\u5927\u5b66\u30c7\u30fc\u30bf\u30b5\u30a4\u30a8\u30f3\u30b9\u5b66\u90e8\u306e\u767d\u6ff5\u6210\u5e0c\u6559\u6388\u3089\u306e\u7814\u7a76\u30b0\u30eb\u30fc\u30d7\u306f\u30012026\u5e7410\u670815\uff5e17\u65e5\u306b\u30a4\u30f3\u30c9\u30cd\u30b7\u30a2\u30fb\u30d0\u30ea\u5cf6\u3067\u958b\u50ac\u3055\u308c\u305f\u56fd\u969b\u4f1a\u8b70\u300cICECCME 2026\u300d\u3067\u3001\u5927\u898f\u6a21\u8a00\u8a9e\u30e2\u30c7\u30eb\uff08LLM\uff09\u306e\u611f\u60c5\u7406\u89e3\u3092\u8a55\u4fa1\u3059\u308b\u7814\u7a76\u6210\u679c\u3092\u767a\u8868\u3057\u307e\u3057\u305f\u3002\u767d\u6ff5\u6559\u6388\u306f15\u65e5\u306b\u53e3\u982d\u767a\u8868\u3092\u884c\u3044\u3001\u6d77\u5916\u306e\u7814\u7a76\u8005\u3068\u6d3b\u767a\u306b\u610f\u898b\u3092\u4ea4\u308f\u3057\u307e\u3057\u305f\u3002 <\/p>\n\n\n\n

\"\"<\/figure>\n\n\n\n

\u5199\u771f1\uff1aICECCME <\/em>2026\u306e\u4f1a\u5834\u3067\u8cea\u7591\u306b\u5bfe\u5fdc\u3059\u308b\u767d\u6ff5\u6559\u6388\u3002<\/em> <\/p>\n\n\n\n

AI\u306f\u4eba\u9593\u3068\u540c\u3058\u3088\u3046\u306b\u300c\u60b2\u3057\u3044\u300d\u3068\u8a55\u4fa1\u3059\u308b\u306e\u304b\uff1f <\/h2>\n\n\n\n

\u5c0f\u8aac\u3092\u8aad\u3093\u3067\u300c\u60b2\u3057\u3044\u300d\u300c\u9a5a\u3044\u305f\u300d\u3068\u611f\u3058\u308b\u5f37\u3055\u306f\u3001\u4eba\u306b\u3088\u3063\u3066\u7570\u306a\u308a\u307e\u3059\u3002\u3067\u306f\u3001ChatGPT\u306a\u3069\u306b\u4f7f\u308f\u308c\u308bLLM\u306f\u3001\u6587\u5b66\u4f5c\u54c1\u306e\u611f\u60c5\u3092\u3069\u306e\u3088\u3046\u306b\u8a55\u4fa1\u3059\u308b\u306e\u3067\u3057\u3087\u3046\u304b\u3002\u4eca\u56de\u306e\u7814\u7a76\u306f\u3001AI\u81ea\u8eab\u306b\u611f\u60c5\u304c\u3042\u308b\u304b\u3092\u8abf\u3079\u308b\u3082\u306e\u3067\u306f\u306a\u304f\u3001AI\u304c\u4ed8\u3051\u305f\u611f\u60c5\u306e\u70b9\u6570\u304c\u4eba\u9593\u306e\u8a55\u4fa1\u306b\u3069\u306e\u7a0b\u5ea6\u8fd1\u3044\u304b<\/strong>\u3092\u79d1\u5b66\u7684\u306b\u691c\u8a3c\u3059\u308b\u3082\u306e\u3067\u3059\u3002 <\/p>\n\n\n\n

\u7814\u7a76\u30b0\u30eb\u30fc\u30d7\u306f\u3001\u65e5\u672c\u8a9e\u306e\u6587\u5b66\u4f5c\u54c13\u4f5c\u54c1\u306b\u3064\u3044\u3066\u3001\u8aad\u8005\u304b\u3089\u5f97\u305f91\u4ef6\u306e\u56de\u7b54\u3092\u3082\u3068\u306b\u3001\u300c\u95a2\u5fc3\u300d\u300c\u9a5a\u304d\u300d\u300c\u60b2\u3057\u307f\u300d\u300c\u6012\u308a\u300d\u306e4\u3064\u306e\u611f\u60c5\u30920\uff5e100\u70b9\u3067\u8868\u3059\u4eba\u9593\u306e\u8a55\u4fa1\u57fa\u6e96\u3092\u4f5c\u6210\u3057\u307e\u3057\u305f\u3002\u305d\u3057\u3066\u30016\u7a2e\u985e\u306eLLM\u306b\u3088\u308b\u8a55\u4fa1\u3068\u6bd4\u8f03\u3002\u3055\u3089\u306b\u3001\u4f5c\u54c1\u3068\u6307\u793a\u6587\u3092\u82f1\u8a9e\u30fb\u4e2d\u56fd\u8a9e\u306b\u7ffb\u8a33\u3057\u305f\u6761\u4ef6\u3067\u3082\u3001\u5404\u30e2\u30c7\u30eb\u306e\u70b9\u6570\u304c\u3069\u3046\u5909\u5316\u3059\u308b\u304b\u3092\u8abf\u3079\u307e\u3057\u305f\u3002 <\/p>\n\n\n\n

\"\"<\/figure>\n\n\n\n

\u56f3\uff1a\u4eba\u9593\u306e\u8a55\u4fa1\u3078\u306e\u8fd1\u3055\u3068\u3001\u7ffb\u8a33\u3057\u305f\u6761\u4ef6\u3067\u306e\u8a55\u4fa1\u306e\u5909\u5316\u3092\u5225\u3005\u306b\u8abf\u3079\u307e\u3057\u305f\u3002<\/em> <\/p>\n\n\n\n

\u300c\u4eba\u9593\u306b\u8fd1\u3044\u8a55\u4fa1\u300d\u3068\u300c\u7ffb\u8a33\u3057\u3066\u3082\u5909\u308f\u3089\u306a\u3044\u8a55\u4fa1\u300d\u306f\u5225\u306e\u3082\u306e <\/h2>\n\n\n\n

\u4eca\u56de\u306e\u5206\u6790\u304b\u3089\u3001\u4eba\u9593\u306e\u611f\u60c5\u8a55\u4fa1\u3068\u306e\u8fd1\u3055\u3068\u3001\u7ffb\u8a33\u3057\u305f\u6761\u4ef6\u3067\u70b9\u6570\u304c\u5909\u308f\u308a\u306b\u304f\u3044\u3053\u3068\u306f\u3001\u7570\u306a\u308b\u6027\u8cea\u3067\u3042\u308b<\/strong>\u3068\u308f\u304b\u308a\u307e\u3057\u305f\u3002\u5b9f\u969b\u3001\u524d\u8005\u3067\u6700\u3082\u8fd1\u3044\u6570\u5024\u3092\u793a\u3057\u305f\u30e2\u30c7\u30eb\u3068\u3001\u5f8c\u8005\u3067\u5909\u5316\u304c\u6700\u3082\u5c0f\u3055\u304b\u3063\u305f\u30e2\u30c7\u30eb\u306f\u7570\u306a\u308a\u307e\u3057\u305f\u3002\u305f\u3060\u3057\u3001\u4eba\u9593\u8a55\u4fa1\u306b\u8fd1\u3044\u4e0a\u4f4d\u30e2\u30c7\u30eb\u306e\u9593\u3067\u3001\u660e\u78ba\u306a\u512a\u52a3\u3092\u78ba\u5b9a\u3067\u304d\u305f\u308f\u3051\u3067\u306f\u3042\u308a\u307e\u305b\u3093\u3002\u307e\u305f\u3001\u4f5c\u54c1\u3084\u611f\u60c5\u306e\u9078\u3073\u65b9\u306b\u3088\u3063\u3066\u30e2\u30c7\u30eb\u306e\u9806\u4f4d\u304c\u5909\u5316\u3057\u307e\u3057\u305f\u3002 <\/p>\n\n\n\n

AI\u306e\u611f\u60c5\u7406\u89e3\u3092\u5358\u7d14\u306a\u30e9\u30f3\u30ad\u30f3\u30b0\u3067\u5224\u65ad\u3059\u308b\u3053\u3068\u306e\u96e3\u3057\u3055\u3092\u793a\u3059\u7d50\u679c\u3067\u3059\u3002\u305f\u3060\u3057\u30013\u4f5c\u54c1\u30fb6\u30e2\u30c7\u30eb\u306b\u3088\u308b\u521d\u671f\u6bb5\u968e\u306e\u691c\u8a3c\u3067\u3042\u308a\u3001\u7d50\u679c\u3092\u3042\u3089\u3086\u308bAI\u306b\u4e00\u822c\u5316\u3059\u308b\u3053\u3068\u306f\u3067\u304d\u307e\u305b\u3093\u3002 <\/p>\n\n\n\n

\u4eba\u9593\u3068\u306e\u6bd4\u8f03\u306f\u65e5\u672c\u8a9e\u306e\u8a55\u4fa1\u3092\u57fa\u6e96\u3068\u3057\u3066\u3044\u307e\u3059\u3002\u82f1\u8a9e\u30fb\u4e2d\u56fd\u8a9e\u306e\u4eba\u9593\u8a55\u4fa1\u3068\u306e\u6bd4\u8f03\u306f\u884c\u3063\u3066\u3044\u307e\u305b\u3093\u3002<\/strong>\u307e\u305f\u3001\u4f5c\u54c1\u3068\u6307\u793a\u6587\u306e\u4e21\u65b9\u3092\u7ffb\u8a33\u3057\u3066\u3044\u308b\u305f\u3081\u3001\u70b9\u6570\u306e\u5909\u5316\u3092\u8a00\u8a9e\u3060\u3051\u3001\u7ffb\u8a33\u3060\u3051\u3001\u3042\u308b\u3044\u306f\u6587\u5316\u306e\u9055\u3044\u3060\u3051\u306e\u5f71\u97ff\u3068\u307f\u306a\u3059\u3053\u3068\u306f\u3067\u304d\u307e\u305b\u3093\u3002 <\/p>\n\n\n\n

\"\"<\/figure>\n\n\n\n

\u5199\u771f2\uff1a\u65e5\u672c\u8a9e\u306e\u4eba\u9593\u8a55\u4fa1\u3092\u57fa\u6e96\u3068\u3057\u305fLLM\u6bd4\u8f03\u7814\u7a76\u306b\u3064\u3044\u3066\u53e3\u982d\u767a\u8868\u3002<\/em> <\/p>\n\n\n\n

\u767a\u8868\u5f8c\u306b\u306f\u3001\u30c9\u30a4\u30c4\u306e\u7814\u7a76\u8005\u304b\u3089\u300c\u4e2d\u56fd\u8a9e\u306b\u7ffb\u8a33\u3057\u305f\u5834\u5408\u3001\u4e2d\u56fd\u767a\u306eLLM\u306b\u306f\u7279\u5fb4\u304c\u73fe\u308c\u308b\u306e\u3067\u306f\u306a\u3044\u304b\u300d\u3068\u306e\u8cea\u554f\u304c\u3042\u308a\u3001\u30e2\u30c7\u30eb\u306e\u7279\u6027\u3084\u591a\u8a00\u8a9e\u8a55\u4fa1\u306b\u3064\u3044\u3066\u8b70\u8ad6\u304c\u4ea4\u308f\u3055\u308c\u307e\u3057\u305f\u3002\u56fd\u969b\u4f1a\u8b70\u3067\u7570\u306a\u308b\u8996\u70b9\u304b\u3089\u610f\u898b\u3092\u5f97\u308b\u3053\u3068\u306f\u3001\u4eca\u5f8c\u306e\u7814\u7a76\u8ab2\u984c\u3092\u8003\u3048\u308b\u8cb4\u91cd\u306a\u6a5f\u4f1a\u306b\u3082\u306a\u308a\u307e\u3057\u305f\u3002 <\/p>\n\n\n\n

\u4fe1\u983c\u3067\u304d\u308bAI\u306e\u8a55\u4fa1\u3078\u2015\u2015\u79d1\u7814\u8cbb\u7814\u7a76\u300cEQ-Fuzzy\u300d\u306b\u3064\u306a\u3050 <\/h2>\n\n\n\n

\u4eba\u3068\u5bfe\u8a71\u3059\u308bAI\u304c\u793e\u4f1a\u306b\u5e83\u304c\u308b\u306a\u304b\u3001\u305d\u306e\u56de\u7b54\u304c\u4eba\u9593\u306e\u611f\u3058\u65b9\u3068\u3069\u306e\u7a0b\u5ea6\u5408\u3063\u3066\u3044\u308b\u306e\u304b\u3001\u6761\u4ef6\u304c\u5909\u308f\u3063\u3066\u3082\u5b89\u5b9a\u3057\u3066\u3044\u308b\u306e\u304b\u3092\u78ba\u304b\u3081\u308b\u3053\u3068\u306f\u91cd\u8981\u3067\u3059\u3002\u5c06\u6765\u7684\u306b\u306f\u3001\u6559\u80b2\u652f\u63f4\u3084\u5229\u7528\u8005\u306b\u914d\u616e\u3057\u305f\u5bfe\u8a71\u30b5\u30fc\u30d3\u30b9\u306a\u3069\u3001AI\u306e\u9069\u5207\u306a\u6d3b\u7528\u3092\u8003\u3048\u308b\u969b\u306e\u8a55\u4fa1\u65b9\u6cd5\u306b\u5f79\u7acb\u3064\u3053\u3068\u304c\u671f\u5f85\u3055\u308c\u307e\u3059\u3002 <\/p>\n\n\n\n

\u767d\u6ff5\u6559\u6388\u3089\u306f\u3053\u308c\u307e\u3067\u3001\u611f\u60c5\u306e\u5f37\u3055\u3092\u9023\u7d9a\u7684\u306a\u6570\u5024\u3067\u8868\u3059\u8a55\u4fa1\u65b9\u6cd5\u3084\u3001LLM\u3054\u3068\u306e\u611f\u60c5\u8a55\u4fa1\u306e\u7279\u5fb4\u306b\u3064\u3044\u3066\u7814\u7a76\u3092\u91cd\u306d\u3066\u304d\u307e\u3057\u305f\u3002\u4eca\u56de\u306e\u6210\u679c\u3082\u305d\u306e\u5ef6\u9577\u7dda\u4e0a\u306b\u3042\u308a\u3001\u79d1\u5b66\u7814\u7a76\u8cbb\u52a9\u6210\u4e8b\u696d\uff08\u79d1\u7814\u8cbb\uff09\u306b\u3088\u308b\u7814\u7a76\u8ab2\u984c\u300c\u30d5\u30a1\u30b8\u30a3\u30a8\u30f3\u30c8\u30ed\u30d4\u30fc\u3068\u30da\u30eb\u30bd\u30ca\u591a\u69d8\u6027\u306b\u57fa\u3065\u304fLLM\u611f\u60c5\u77e5\u80fd\u306e\u4e0d\u78ba\u5b9f\u6027\u8a55\u4fa1\uff08EQ-Fuzzy\uff09\u300d\u306b\u3064\u306a\u304c\u308b\u53d6\u308a\u7d44\u307f\u3067\u3059\u3002\u4eca\u5f8c\u306f\u3001\u611f\u60c5\u8a55\u4fa1\u306e\u66d6\u6627\u3055\u3084\u4e0d\u78ba\u5b9f\u6027\u3082\u542b\u3081\u3066\u3001\u591a\u9762\u7684\u306bAI\u3092\u8a55\u4fa1\u3059\u308b\u7814\u7a76\u3092\u9032\u3081\u307e\u3059\u3002 <\/p>\n\n\n\n

\u3053\u3046\u3057\u305f\u7814\u7a76\u306f\u3001AI\u3092\u300c\u4f7f\u3046\u300d\u3060\u3051\u3067\u306a\u304f\u3001\u305d\u306e\u80fd\u529b\u3084\u9650\u754c\u3092\u30c7\u30fc\u30bf\u306b\u57fa\u3065\u3044\u3066\u691c\u8a3c\u3059\u308b\u3068\u3044\u3046\u3001\u30c7\u30fc\u30bf\u30b5\u30a4\u30a8\u30f3\u30b9\u306e\u5b66\u3073\u306e\u9762\u767d\u3055\u3082\u793a\u3057\u3066\u3044\u307e\u3059\u3002 <\/p>\n\n\n\n

\u767a\u8868\u3057\u305f\u56fd\u969b\u4f1a\u8b70\u306b\u3064\u3044\u3066 <\/h2>\n\n\n\n

ICECCME\uff08International Conference on Electrical, Computer, Communications and Mechatronics Engineering\uff09\u306f\u3001\u96fb\u6c17\u30fb\u96fb\u5b50\u3001\u60c5\u5831\u901a\u4fe1\u3001\u4eba\u5de5\u77e5\u80fd\u306a\u3069\u5e45\u5e83\u3044\u5de5\u5b66\u5206\u91ce\u3092\u5bfe\u8c61\u3068\u3059\u308b\u56fd\u969b\u4f1a\u8b70\u3067\u3059\u30022026\u5e74\u306f\u7b2c6\u56de\u5927\u4f1a\u306b\u3042\u305f\u308a\u3001\u4e3b\u50ac\u8005\u306b\u3088\u308b\u3068<\/a>\u30012021\uff5e2025\u5e74\u306e\u5404\u5927\u4f1a\u306e\u767a\u8868\u8ad6\u6587\u306fIEEE\u306e\u5b66\u8853\u6587\u732e\u30c7\u30fc\u30bf\u30d9\u30fc\u30b9\u300cIEEE Xplore\u300d\u306b\u63b2\u8f09\u3055\u308c\u3001Scopus\u306b\u3082\u53ce\u9332\u3055\u308c\u3066\u3044\u307e\u3059\u30022026\u5e74\u5927\u4f1a\u306b\u3064\u3044\u3066\u3082\u3001\u63a1\u629e\u30fb\u767a\u8868\u8ad6\u6587\u306fIEEE Xplore\u306e\u53ce\u9332\u5be9\u67fb\u304a\u3088\u3073Scopus\u3078\u306e\u53ce\u9332\u7533\u8acb\u304c\u4e88\u5b9a\u3055\u308c\u3066\u3044\u307e\u3059\u3002 <\/p>\n\n\n\n

\"\"<\/figure>\n\n\n\n

\u5199\u771f3\uff1a\u4f1a\u5834\u3067\u53c2\u52a0\u8a3c\u660e\u66f8\u3092\u624b\u306b\u3059\u308b\u767d\u6ff5\u6559\u6388\uff08\u53f3\uff09\u3002\u53c2\u52a0\u8a3c\u660e\u66f8\u306f\u53d7\u8cde\u8a3c\u660e\u66f8\u3067\u306f\u3042\u308a\u307e\u305b\u3093\u3002<\/em> <\/p>\n\n\n\n

\u767a\u8868\u8ad6\u6587\u30fb\u7814\u7a76\u652f\u63f4 <\/h2>\n\n\n\n

\u8ad6\u6587\u984c\u76ee<\/strong> <\/p>\n\n\n\n

A Compact Japanese-Human-Grounded Benchmark for Literary Emotion Understanding with English\/Chinese Robustness Probes <\/p>\n\n\n\n

\u8457\u8005<\/strong> <\/p>\n\n\n\n

Naruki Shirahama\uff08\u767d\u6ff5\u6210\u5e0c\uff09\u3001Yuma Yoshimoto\u3001Naofumi Nakaya\u3001Junji Nishino\u3001Satoshi Watanabe <\/p>\n\n\n\n

\u767a\u8868<\/strong> <\/p>\n\n\n\n

ICECCME 2026\u30012026\u5e7410\u670815\u65e5\u3001\u30a4\u30f3\u30c9\u30cd\u30b7\u30a2\u30fb\u30d0\u30ea\u5cf6\uff08Paper ID: 648\uff09 <\/p>\n\n\n\n

\u7814\u7a76\u652f\u63f4<\/strong> <\/p>\n\n\n\n

JSPS\u79d1\u7814\u8cbb\uff08\u8ab2\u984c\u756a\u53f7 26K14983<\/a>\u300124K13350<\/a>\uff09\u306e\u4e00\u90e8\u652f\u63f4\u3092\u53d7\u3051\u3066\u3044\u307e\u3059\u3002 <\/p>\n\n\n\n

\u5927\u4f1a\u516c\u5f0f\u30b5\u30a4\u30c8<\/strong> <\/p>\n\n\n\n

ICECCME 2026<\/a> <\/p>\n\n\n\n

How does AI read sadness in fiction? Professor Shirahama and colleagues present research at ICECCME 2026 <\/h1>\n\n\n\n

A research team including Professor Naruki Shirahama of the Faculty of Data Science at Shimonoseki City University presented its work on evaluating emotion understanding in large language models (LLMs) at ICECCME 2026, held in Bali, Indonesia, on 15\u201317 October 2026. Professor Shirahama gave an oral presentation on 15 October and exchanged ideas with researchers from abroad. <\/p>\n\n\n\n

\"\"<\/figure>\n\n\n\n

Photo 1. Professor Shirahama responding to questions at ICECCME 2026.<\/em> <\/p>\n\n\n\n

Does AI rate sadness in the same way as people? <\/h2>\n\n\n\n

A story may leave one reader deeply saddened and another only mildly moved. How do LLMs\u2014the technology behind services such as ChatGPT\u2014rate emotion in literature? This study does not investigate whether AI has feelings of its own. It examines how closely the emotion scores produced by AI match human ratings<\/strong>. <\/p>\n\n\n\n

The team used 91 reader responses to establish a human reference for three Japanese literary works. Readers rated four dimensions\u2014interest, surprise, sadness and anger\u2014on a scale from 0 to 100. The researchers compared these ratings with scores from six LLMs. They also examined how each model\u2019s scores changed when both the literary texts and task instructions were translated into English or Chinese. <\/p>\n\n\n\n

\"\"<\/figure>\n\n\n\n

Figure. Agreement with human ratings and changes under translated conditions were evaluated separately.<\/em> <\/p>\n\n\n\n

Matching human ratings and remaining stable after translation are different qualities <\/h2>\n\n\n\n

The analysis showed that agreement with human emotion ratings and stability under translated conditions are distinct qualities<\/strong>. The model with the closest observed match to human ratings was different from the one whose scores changed the least under translation. However, the study did not establish a clear winner among the models with the closest human alignment. Model rankings also changed when the selection of works or emotion dimensions was altered. <\/p>\n\n\n\n

These findings show why a simple ranking can be misleading when assessing AI emotion understanding. This was an early-stage study of three literary works and six models, so its findings cannot be generalized to all AI systems. <\/p>\n\n\n\n

The human comparison used Japanese ratings as its reference. No comparisons with human ratings in English or Chinese were conducted.<\/strong> Because both the texts and instructions were translated, changes in scores cannot be attributed solely to language, translation or cultural differences. <\/p>\n\n\n\n

\"\"<\/figure>\n\n\n\n

Photo 2. Presenting the LLM comparison study grounded in Japanese human ratings.<\/em> <\/p>\n\n\n\n

After the presentation, a researcher from Germany asked whether LLMs developed in China might show distinctive patterns when the texts were translated into Chinese. The question prompted discussion of model characteristics and multilingual evaluation. Perspectives shared at international conferences can help shape questions for future research. <\/p>\n\n\n\n

Toward trustworthy AI evaluation: connecting with EQ-Fuzzy <\/h2>\n\n\n\n

As conversational AI becomes more widely used, it is important to examine how well its responses reflect human judgments and how stable they remain when conditions change. In the future, evaluation methods of this kind may help inform appropriate uses of AI, including educational support and dialogue services that are sensitive to users\u2019 needs. <\/p>\n\n\n\n

Professor Shirahama and his collaborators have previously studied methods for expressing emotion intensity on continuous numerical scales, as well as differences in emotion ratings across LLMs. The present work builds on that research and connects with EQ-Fuzzy, a project supported by Japan\u2019s Grants-in-Aid for Scientific Research (KAKENHI) that evaluates uncertainty in LLM emotional intelligence using fuzzy entropy and persona diversity. The team plans to develop a more comprehensive approach to AI evaluation that takes ambiguity and uncertainty in emotion ratings into account. <\/p>\n\n\n\n

This research also illustrates the appeal of studying data science: going beyond using AI to examining its capabilities and limitations through evidence. <\/p>\n\n\n\n

About the conference <\/h2>\n\n\n\n

ICECCME\u2014the International Conference on Electrical, Computer, Communications and Mechatronics Engineering\u2014covers a broad range of engineering fields, including electrical and electronic engineering, information and communications, and artificial intelligence. The 2026 event was its sixth edition. According to the organizers<\/a>, papers from the 2021\u20132025 conferences have been published in IEEE Xplore and indexed in Scopus. For 2026, accepted and presented papers are planned for submission to IEEE Xplore, subject to its scope and quality requirements, and for submission to Scopus for indexing. <\/p>\n\n\n\n

\"\"<\/figure>\n\n\n\n

Photo 3. Professor Shirahama (right) with a certificate of participation at the venue. This is a participation certificate, not an award certificate.<\/em> <\/p>\n\n\n\n

Paper and research support <\/h2>\n\n\n\n

Title<\/strong> <\/p>\n\n\n\n

A Compact Japanese-Human-Grounded Benchmark for Literary Emotion Understanding with English\/Chinese Robustness Probes <\/p>\n\n\n\n

Authors<\/strong> <\/p>\n\n\n\n

Naruki Shirahama\uff08\u767d\u6ff5\u6210\u5e0c\uff09, Yuma Yoshimoto, Naofumi Nakaya, Junji Nishino, Satoshi Watanabe <\/p>\n\n\n\n

Presentation<\/strong> <\/p>\n\n\n\n

ICECCME 2026, 15 October 2026, Bali, Indonesia (Paper ID: 648) <\/p>\n\n\n\n

Funding<\/strong> <\/p>\n\n\n\n

This work was partially supported by JSPS KAKENHI, Grant Numbers 26K14983<\/a> and 24K13350<\/a>. <\/p>\n\n\n\n

Conference website<\/strong> <\/p>\n\n\n\n

ICECCME 2026<\/a> <\/p>\n","protected":false},"excerpt":{"rendered":"

\u4e0b\u95a2\u5e02\u7acb\u5927\u5b66\u30c7\u30fc\u30bf\u30b5\u30a4\u30a8\u30f3\u30b9\u5b66\u90e8\u306e\u767d\u6ff5\u6210\u5e0c\u6559\u6388\u3089\u306e\u7814\u7a76\u30b0\u30eb\u30fc\u30d7\u306f\u30012026\u5e7410\u670815\uff5e17\u65e5\u306b\u30a4\u30f3\u30c9\u30cd\u30b7\u30a2\u30fb\u30d0\u30ea\u5cf6\u3067\u958b\u50ac\u3055\u308c\u305f\u56fd\u969b\u4f1a\u8b70\u300cICECCME 2026\u300d\u3067\u3001\u5927\u898f\u6a21\u8a00\u8a9e\u30e2\u30c7\u30eb\uff08LLM\uff09\u306e\u611f\u60c5\u7406\u89e3\u3092\u8a55\u4fa1\u3059\u308b\u7814\u7a76\u6210\u679c\u3092\u767a\u8868\u3057\u307e\u3057\u305f\u3002\u767d\u6ff5\u6559\u6388\u306f15\u65e5\u306b\u53e3\u982d […]<\/p>\n","protected":false},"author":26,"featured_media":1065,"comment_status":"closed","ping_status":"closed","sticky":false,"template":"","format":"standard","meta":{"_acf_changed":false,"footnotes":""},"categories":[2,1],"class_list":["post-1062","post","type-post","status-publish","format-standard","has-post-thumbnail","hentry","category-education","category-research"],"acf":[],"publishpress_future_action":{"enabled":false,"date":"2026-11-09 18:33:29","action":"change-status","newStatus":"draft","terms":[],"taxonomy":"category","extraData":[]},"publishpress_future_workflow_manual_trigger":{"enabledWorkflows":[]},"_links":{"self":[{"href":"https:\/\/www.shimonoseki-cu.ac.jp\/sdgs\/wp-json\/wp\/v2\/posts\/1062","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/www.shimonoseki-cu.ac.jp\/sdgs\/wp-json\/wp\/v2\/posts"}],"about":[{"href":"https:\/\/www.shimonoseki-cu.ac.jp\/sdgs\/wp-json\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"https:\/\/www.shimonoseki-cu.ac.jp\/sdgs\/wp-json\/wp\/v2\/users\/26"}],"replies":[{"embeddable":true,"href":"https:\/\/www.shimonoseki-cu.ac.jp\/sdgs\/wp-json\/wp\/v2\/comments?post=1062"}],"version-history":[{"count":3,"href":"https:\/\/www.shimonoseki-cu.ac.jp\/sdgs\/wp-json\/wp\/v2\/posts\/1062\/revisions"}],"predecessor-version":[{"id":1076,"href":"https:\/\/www.shimonoseki-cu.ac.jp\/sdgs\/wp-json\/wp\/v2\/posts\/1062\/revisions\/1076"}],"wp:featuredmedia":[{"embeddable":true,"href":"https:\/\/www.shimonoseki-cu.ac.jp\/sdgs\/wp-json\/wp\/v2\/media\/1065"}],"wp:attachment":[{"href":"https:\/\/www.shimonoseki-cu.ac.jp\/sdgs\/wp-json\/wp\/v2\/media?parent=1062"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/www.shimonoseki-cu.ac.jp\/sdgs\/wp-json\/wp\/v2\/categories?post=1062"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}